© 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. 0-RES-JB
    11. 4023
    Prev
    Next
    INDEX
    Explanations

    IQ related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence and emotional quotient assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elle
    -0.72
    unal
    -0.68
    sels
    -0.68
    gren
    -0.68
    lement
    -0.67
    andal
    -0.67
    walker
    -0.64
    cher
    -0.64
    shore
    -0.63
     wrapping
    -0.63
    POSITIVE LOGITS
     IQ
    4.01
    IQ
    2.49
     GPA
    1.34
     EEG
    1.34
     EQ
    1.28
     intellect
    1.28
     MMR
    1.24
     Intelligence
    1.18
     intelligence
    1.17
    intelligence
    1.14
    Activations Density 0.017%

    No Known Activations