© 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. 3-RES-JB
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    descriptions of nature and landscapes that evoke a sense of beauty

    oai_token-act-pair · gpt-3.5-turbo

    evocative descriptions of nature and beauty

    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
    untled
    -0.80
    endment
    -0.78
    osponsors
    -0.72
     Username
    -0.70
    eve
    -0.70
    afety
    -0.69
     Petition
    -0.69
    emort
    -0.69
     Discussion
    -0.69
     notified
    -0.69
    POSITIVE LOGITS
     nause
    0.83
     ecstasy
    0.80
     melanch
    0.78
     unforgettable
    0.76
     throb
    0.75
     homage
    0.74
    .).
    0.73
     decad
    0.73
    }.
    0.72
     heroine
    0.72
    Activations Density 2.915%

    No Known Activations