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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 20238
    Prev
    Next
    INDEX
    Explanations

    words related to physical bodily reactions or sensations

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of intense physical and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OURCE
    -0.73
     Spons
    -0.70
     Compliance
    -0.69
     disadvant
    -0.69
    orthy
    -0.68
     [+
    -0.67
    ofer
    -0.67
    edIn
    -0.65
     Applicant
    -0.65
     Worldwide
    -0.64
    POSITIVE LOGITS
     tremb
    1.33
     froze
    1.26
     freezes
    1.12
     explodes
    1.10
     throb
    1.08
     twitch
    1.07
     screamed
    1.06
     vibr
    1.05
     wob
    1.04
     melts
    0.99
    Activations Density 0.152%

    No Known Activations