© 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. 4-RES-JB
    11. 12512
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate news or business updates

    oai_token-act-pair · gpt-3.5-turbo

    references to companies, organizations, or notable events related to business activities

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

    No Comments

    Negative Logits
    croft
    -0.73
    zek
    -0.72
    yk
    -0.68
    umatic
    -0.68
    _(
    -0.65
    velt
    -0.65
    ï¸
    -0.63
     hatch
    -0.63
     spoilers
    -0.60
     regress
    -0.60
    POSITIVE LOGITS
     Cosponsors
    0.87
     headquartered
    0.86
     initials
    0.79
    ãĤ¤ãĥĪ
    0.76
    actionDate
    0.75
     subsidiaries
    0.71
    lishes
    0.70
    ngth
    0.69
     maintains
    0.65
     headquarters
    0.65
    Activations Density 0.907%

    No Known Activations