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. 6-RES-JB
    6. 3022
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or consequences happening as a result of certain conditions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    special formatting or structure in the text, like separators or annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritz
    -0.67
     redes
    -0.63
     SERV
    -0.62
    ipl
    -0.60
     unden
    -0.58
    iliated
    -0.56
     earthqu
    -0.56
     Gors
    -0.56
    gross
    -0.56
     enthusi
    -0.56
    POSITIVE LOGITS
    osterone
    0.88
    ulhu
    0.86
    tenance
    0.85
    terday
    0.82
    ilet
    0.81
    stairs
    0.79
    '-
    0.75
    uty
    0.74
    lihood
    0.73
    getic
    0.71
    Activations Density 0.155%

    No Known Activations