© 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. 10-RES-JB
    11. 23256
    Prev
    Next
    INDEX
    Explanations

    phrases related to approaches or characteristics, often with positive or charitable connotations

    oai_token-act-pair · gpt-3.5-turbo

    descriptors indicating community, approach, and inclusive characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.81
    registered
    -0.76
    Invalid
    -0.75
    ievers
    -0.74
    hots
    -0.73
    acers
    -0.72
    ivably
    -0.71
    unknown
    -0.71
    equal
    -0.71
    eligible
    -0.69
    POSITIVE LOGITS
     nature
    1.89
     attitude
    1.68
     approach
    1.61
     demeanor
    1.55
     ethos
    1.53
     mentality
    1.50
     stance
    1.45
     mindset
    1.43
     vibe
    1.41
     outlook
    1.37
    Activations Density 0.343%

    No Known Activations