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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8912
    Prev
    Next
    INDEX
    Explanations

    superlatives or intensifiers conveying a high level of extremity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm or high praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.75
    Reloaded
    -0.75
    edIn
    -0.70
     Transcript
    -0.69
     Lauder
    -0.69
     Supported
    -0.66
     Anger
    -0.66
     Qiao
    -0.65
    endor
    -0.63
     Frie
    -0.63
    POSITIVE LOGITS
    imposed
    1.31
    nova
    1.24
    visor
    1.14
    charged
    1.11
    cedes
    1.08
    powers
    1.03
    computer
    0.97
    charg
    0.94
    visory
    0.94
    charging
    0.92
    Activations Density 0.014%

    No Known Activations