© 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. 7-RES-JB
    11. 8760
    Prev
    Next
    INDEX
    Explanations

    objects or actions associated with physical movements or changes in position

    oai_token-act-pair · gpt-3.5-turbo

    objects or components involved in various actions or scenarios

    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
     pestic
    -0.69
    SPONSORED
    -0.67
    NetMessage
    -0.65
    annot
    -0.60
    ĨĴ
    -0.59
    Marsh
    -0.59
    KNOWN
    -0.58
     therap
    -0.58
     Riding
    -0.58
     existential
    -0.57
    POSITIVE LOGITS
     accordingly
    0.91
    washer
    0.84
     onto
    0.81
     lid
    0.81
    glass
    0.80
     prematurely
    0.79
     into
    0.76
     drawer
    0.75
     button
    0.74
     properly
    0.74
    Activations Density 0.417%

    No Known Activations