© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    descriptions related to personal and financial responsibilities with children

    oai_token-act-pair · gpt-3.5-turbo

    themes related to emotional and spiritual well-being in relation to family and career

    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
    ffen
    -0.58
     *)
    -0.54
     Axel
    -0.54
     overw
    -0.54
    poll
    -0.53
     hindsight
    -0.52
    iversary
    -0.51
     sequels
    -0.51
     Presbyter
    -0.50
    lim
    -0.50
    POSITIVE LOGITS
     respectively
    0.94
     abound
    0.65
    etc
    0.64
    depending
    0.59
    umers
    0.55
     whichever
    0.55
    anguages
    0.54
     whatsoever
    0.54
     conducive
    0.54
    ĸļ
    0.53
    Activations Density 1.478%

    No Known Activations