© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7073
    Prev
    Next
    INDEX
    Explanations

    words related to psychology and psychometry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychology and psychometric assessments

    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
    FORE
    -0.78
     Loyal
    -0.71
    holder
    -0.71
    LOAD
    -0.70
     Graveyard
    -0.70
     Lions
    -0.69
     bearer
    -0.69
    BACK
    -0.68
     Palmer
    -0.66
     Darkness
    -0.65
    POSITIVE LOGITS
    otherapy
    1.46
    otic
    1.41
    odynamic
    1.40
    osis
    1.33
    ologically
    1.30
    odynam
    1.30
    okin
    1.28
    otropic
    1.24
    otics
    1.24
    ophys
    1.23
    Activations Density 0.025%

    No Known Activations