© 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. 9-RES-JB
    6. 9015
    Prev
    Next
    INDEX
    Explanations

    years, specifically the year 2002

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly 2001 and 2002

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    place
    -0.81
    hop
    -0.65
    bars
    -0.65
    places
    -0.64
    heet
    -0.62
    queue
    -0.61
    hops
    -0.61
    este
    -0.60
    ledged
    -0.59
    edly
    -0.58
    POSITIVE LOGITS
    -'
    0.97
    å¹
    0.80
    ĸļ
    0.78
    ãĥĥãĥī
    0.76
     Anniversary
    0.65
     vintage
    0.64
    iyah
    0.63
     onwards
    0.63
    â̲
    0.62
     Fuk
    0.61
    Activations Density 0.063%

    No Known Activations