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

    Neuronpedia

    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. 6-RES-JB
    11. 7273
    Prev
    Next
    INDEX
    Explanations

    actions or events that involve physical intervention or movement

    oai_token-act-pair · gpt-3.5-turbo

    verbs describing actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾į
    -0.76
    emen
    -0.65
    Eastern
    -0.61
    dimension
    -0.61
     nutshell
    -0.60
    arger
    -0.58
    edge
    -0.58
     totality
    -0.55
     twilight
    -0.54
    Enlarge
    -0.53
    POSITIVE LOGITS
    ERY
    0.69
    ifully
    0.69
    ModLoader
    0.69
     etc
    0.68
    agher
    0.65
    jri
    0.63
    akespeare
    0.62
    ograp
    0.61
    Downloadha
    0.61
    hement
    0.60
    Activations Density 0.296%

    No Known Activations