© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6862
    Prev
    Next
    INDEX
    Explanations

    words related to directions or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    references to various metaphorical or literal paths in the context of progression or decision-making

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

    No Comments

    Negative Logits
    zona
    -0.72
     Sanct
    -0.67
     sterling
    -0.64
    ilings
    -0.64
     Nationals
    -0.63
    orpor
    -0.61
    rongh
    -0.60
     NOTICE
    -0.59
    ENCY
    -0.58
    igne
    -0.58
    POSITIVE LOGITS
    finding
    1.16
     paths
    1.13
    finder
    1.02
    ogen
    1.01
    ways
    0.96
     path
    0.92
    find
    0.90
    ologies
    0.85
    =/
    0.83
    nob
    0.81
    Activations Density 0.019%

    No Known Activations