© 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. 4-RES-JB
    11. 15247
    Prev
    Next
    INDEX
    Explanations

    abstract concepts related to formality and structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to forms and characteristics of reality

    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
    kers
    -0.75
    vier
    -0.74
    fman
    -0.74
    Ļ½
    -0.73
    ERC
    -0.71
    secut
    -0.70
    kef
    -0.69
    ergy
    -0.69
    rompt
    -0.68
    vag
    -0.67
    POSITIVE LOGITS
    istically
    0.74
    atsu
    0.70
    butt
    0.68
    heads
    0.66
     Explosion
    0.64
    hound
    0.64
    ativity
    0.63
     Cloak
    0.63
    ipop
    0.61
    aries
    0.61
    Activations Density 0.019%

    No Known Activations