© 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. 8-RES-JB
    11. 1809
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to personal growth and empowerment

    oai_token-act-pair · gpt-3.5-turbo

    themes of personal growth and positive change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mun
    -0.60
     widespread
    -0.60
    cise
    -0.59
    published
    -0.56
    EMP
    -0.56
     carcin
    -0.55
     extensive
    -0.55
    installed
    -0.54
    Downloadha
    -0.54
    industrial
    -0.53
    POSITIVE LOGITS
     Yourself
    1.10
     yourselves
    0.93
     oneself
    0.91
     yourself
    0.88
    !.
    0.80
     sacrific
    0.79
     spiritually
    0.79
     creatively
    0.78
    !,
    0.78
     offensively
    0.75
    Activations Density 0.531%

    No Known Activations