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. 12825
    Prev
    Next
    INDEX
    Explanations

    words containing 'rep' as a sequence

    oai_token-act-pair · gpt-3.5-turbo

    the various forms of the word "rep" (short for representative or related terms)

    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
    istically
    -0.65
    scape
    -0.60
    RL
    -0.59
    wolf
    -0.59
    BIP
    -0.58
     Joyce
    -0.57
     Learns
    -0.56
    OTA
    -0.55
     pooled
    -0.53
     Sands
    -0.53
    POSITIVE LOGITS
    ublic
    1.52
    resents
    1.05
    orters
    1.00
    ngth
    0.96
    endant
    0.91
    ulse
    0.91
    atri
    0.89
    rint
    0.87
    rising
    0.86
    endants
    0.85
    Activations Density 0.043%

    No Known Activations