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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15431
    Prev
    Next
    INDEX
    Explanations

    quotations and phrases with a negative connotation or critical tone

    oai_token-act-pair · gpt-3.5-turbo

    phrases or quotes that describe actions or characteristics attributed to entities

    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
     ********************************
    -0.70
    mentioned
    -0.65
    ersen
    -0.64
     accordingly
    -0.64
    cies
    -0.64
    bg
    -0.60
    then
    -0.60
    msg
    -0.59
    ixie
    -0.59
    onga
    -0.59
    POSITIVE LOGITS
     conduit
    0.79
     distraction
    0.74
     nuisance
    0.72
     gateway
    0.72
     legitimate
    0.72
     precursor
    0.69
     prerequisite
    0.67
     definitive
    0.67
     singular
    0.66
     distinct
    0.65
    Activations Density 0.473%

    No Known Activations