© 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. 3-RES-JB
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    specific actions or operations described with strong verbs

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles that indicate actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifi
    -0.84
    ascript
    -0.77
    ocrates
    -0.77
    iosis
    -0.76
    eday
    -0.71
    OPE
    -0.69
    haps
    -0.69
    ensis
    -0.67
    olog
    -0.67
    efer
    -0.66
    POSITIVE LOGITS
     ability
    0.90
     sphere
    0.85
     agent
    0.83
     element
    0.83
     realization
    0.81
     tendency
    0.80
     effort
    0.78
     mechanism
    0.77
     impulse
    0.76
     superpower
    0.74
    Activations Density 0.354%

    No Known Activations