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. 9-RES-JB
    6. 7519
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization or movement known as "Naxalites"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or ideology associated with violence

    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
    âĺħâĺħ
    -0.70
     Shades
    -0.63
     FI
    -0.61
     ja
    -0.60
    ufact
    -0.59
     disapprove
    -0.59
     unfor
    -0.58
    à¨
    -0.58
     psychiat
    -0.57
     fry
    -0.55
    POSITIVE LOGITS
    xon
    1.37
    xus
    1.35
    seed
    1.05
    xes
    1.00
    anth
    0.95
    avier
    0.95
    ylon
    0.95
    angel
    0.94
    xi
    0.93
    imum
    0.92
    Activations Density 0.046%

    No Known Activations