© 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. 9-RES-JB
    11. 18580
    Prev
    Next
    INDEX
    Explanations

    references to sales and revenue estimation

    oai_token-act-pair · gpt-3.5-turbo

    references to sales figures and related financial metrics

    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
    icz
    -0.68
     Schne
    -0.67
     sshd
    -0.67
    oss
    -0.66
    atever
    -0.65
     Lak
    -0.63
    OSE
    -0.62
    --+
    -0.61
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    aque
    -0.59
    POSITIVE LOGITS
    manship
    1.21
    people
    1.12
    person
    1.11
    force
    1.07
    hips
    1.03
    pers
    0.95
    women
    0.92
    woman
    0.88
    hare
    0.87
    men
    0.87
    Activations Density 0.039%

    No Known Activations