© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12078
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action to resolve an issue

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "ending" or "putting an end to" situations, particularly in a context of responsibility or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Availability
    -0.63
     immensely
    -0.59
     unfocusedRange
    -0.58
    Ka
    -0.58
    iott
    -0.58
     Frequ
    -0.57
    scl
    -0.57
    imity
    -0.57
    animous
    -0.56
    elligence
    -0.55
    POSITIVE LOGITS
    channelAvailability
    0.75
     ILCS
    0.73
     lid
    0.69
     overboard
    0.68
     aside
    0.68
     Canaver
    0.67
    igham
    0.67
    together
    0.67
     leash
    0.64
     emphasis
    0.64
    Activations Density 0.140%

    No Known Activations