© 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. 4-RES-JB
    11. 11048
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations or planning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization and planning, particularly in a biological or structured context

    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
    aniel
    -0.65
     pse
    -0.63
    eeper
    -0.63
    orters
    -0.62
     DRAG
    -0.60
    reon
    -0.60
     certific
    -0.59
     MUST
    -0.59
     showc
    -0.58
     blazing
    -0.58
    POSITIVE LOGITS
    axy
    0.95
    oid
    0.91
    osaurs
    0.84
    tenance
    0.81
    amental
    0.81
    ation
    0.80
    actic
    0.80
     spores
    0.79
    ifax
    0.78
    veyard
    0.77
    Activations Density 0.025%

    No Known Activations