© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 11206
    Prev
    Next
    INDEX
    Explanations

    references to taking specific actions or making decisions in response to a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning the concept of "action" being taken or required

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orf
    -0.66
    gling
    -0.63
    conservancy
    -0.63
     abund
    -0.63
    ench
    -0.60
    population
    -0.59
     porous
    -0.59
     veiled
    -0.59
    BALL
    -0.59
     Argon
    -0.58
    POSITIVE LOGITS
     against
    0.86
    ivism
    0.86
    iveness
    0.84
    ional
    0.84
    able
    0.82
    igraph
    0.76
     committees
    0.75
    ulatory
    0.75
     ACTIONS
    0.75
    aries
    0.75
    Activations Density 0.033%

    No Known Activations