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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 14610
    Prev
    Next
    INDEX
    Explanations

    discussion or critique about politicians and political events

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions and significant experiences

    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
     TEAM
    -0.71
    clusive
    -0.70
     Phase
    -0.69
     OG
    -0.68
     Formation
    -0.66
     Documents
    -0.65
     ABV
    -0.65
    senal
    -0.64
    BAT
    -0.64
     Coverage
    -0.64
    POSITIVE LOGITS
     doubtless
    1.20
     pity
    1.18
     understandably
    1.15
     nostalg
    1.14
     scorn
    1.12
     surely
    1.11
     unconsciously
    1.10
     wonder
    1.09
     lament
    1.08
     subconscious
    1.08
    Activations Density 0.962%

    No Known Activations