© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 24093
    Prev
    Next
    INDEX
    Explanations

    years, particularly the year 1979

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1979 and its significance in various contexts

    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
    hed
    -0.73
    hop
    -0.71
    uden
    -0.69
    Rail
    -0.67
     entirety
    -0.66
     ship
    -0.65
    phas
    -0.64
     lawy
    -0.61
     limb
    -0.60
    Ship
    -0.60
    POSITIVE LOGITS
    å¹
    0.80
    -'
    0.73
     ILCS
    0.70
     nostalg
    0.69
     onwards
    0.68
    isSpecialOrderable
    0.68
    1982
    0.66
    1967
    0.65
    1968
    0.65
    monton
    0.64
    Activations Density 0.022%

    No Known Activations