© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2043
    Prev
    Next
    INDEX
    Explanations

    words related to periods of time, specifically focusing on the second half of events

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific segment of a game or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.71
    Reviewed
    -0.67
    achus
    -0.64
    kinson
    -0.63
    atro
    -0.62
    HCR
    -0.61
    orge
    -0.61
    votes
    -0.60
    cler
    -0.59
    incinn
    -0.59
    POSITIVE LOGITS
    heartedly
    0.85
    pipe
    0.80
    terness
    0.74
    enium
    0.68
    stop
    0.67
     Cec
    0.66
    foundland
    0.66
     Nieto
    0.65
    arse
    0.65
     thereof
    0.64
    Activations Density 0.017%

    No Known Activations