Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22907
    Prev
    Next
    INDEX
    Explanations

    adjectives related to size and significance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and quantifiers related to size and status

    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
     Wilde
    -0.65
    natureconservancy
    -0.59
     Learns
    -0.58
     Immunity
    -0.57
    Dialogue
    -0.55
     McKenna
    -0.55
     Kills
    -0.54
     COVER
    -0.54
     speech
    -0.53
     wound
    -0.53
    POSITIVE LOGITS
    tenance
    1.31
    terday
    1.18
    lihood
    1.05
    yright
    1.04
    osterone
    1.02
    erie
    0.97
    alog
    0.97
    alyst
    0.96
    ousand
    0.95
    ruction
    0.95
    Activations Density 0.288%

    No Known Activations