© 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. 3-RES-JB
    11. 12173
    Prev
    Next
    INDEX
    Explanations

    acronyms starting with 'WH'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific vulnerabilities or security issues related to "WH" entities or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.81
     Mercer
    -0.78
    ãĤª
    -0.72
     Gillespie
    -0.71
    ger
    -0.71
     Volks
    -0.70
    spection
    -0.70
     Bulg
    -0.69
     Belg
    -0.68
    ification
    -0.67
    POSITIVE LOGITS
    ILE
    1.15
    YY
    1.14
    WH
    1.04
    ICH
    0.99
    INESS
    0.94
    ITNESS
    0.94
    LY
    0.94
    HA
    0.93
    OA
    0.91
    AX
    0.89
    Activations Density 0.008%

    No Known Activations