Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21903
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to suffering and suffocation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suff" and its various forms, indicating a focus on themes of suffering or deprivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.73
     Noir
    -0.70
    iannopoulos
    -0.69
     Bravo
    -0.68
     neigh
    -0.67
    STEP
    -0.66
    REF
    -0.65
     Qiao
    -0.64
    å°Ĩ
    -0.64
    CHR
    -0.64
    POSITIVE LOGITS
    erers
    1.44
    erer
    1.30
    ocating
    1.23
    ocation
    1.17
    ocated
    1.12
    ocate
    1.11
    rag
    1.11
    rage
    1.08
    iments
    1.02
    iment
    1.01
    Activations Density 0.036%

    No Known Activations