© 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. 8-RES-JB
    11. 2726
    Prev
    Next
    INDEX
    Explanations

    technological tools and platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with protection and security in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ones
    -0.64
    ussions
    -0.64
    rogens
    -0.62
     Highlander
    -0.62
    racuse
    -0.61
    stad
    -0.59
     Sections
    -0.58
    nant
    -0.56
     Moz
    -0.55
     Distribut
    -0.54
    POSITIVE LOGITS
    âĺ
    0.74
    ĸļ
    0.72
    eworld
    0.72
    mma
    0.72
     selves
    0.72
    é¾įåĸļ士
    0.68
    adle
    0.64
    ultimate
    0.64
    ãĥ¯
    0.63
     spree
    0.62
    Activations Density 0.542%

    No Known Activations