© 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. 9-RES-JB
    11. 14360
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles about various topics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    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
     adolescence
    -0.77
     enriched
    -0.75
     recomm
    -0.72
     resilience
    -0.69
    orno
    -0.68
     challeng
    -0.67
     ageing
    -0.67
     defe
    -0.66
     arming
    -0.66
     underestimate
    -0.66
    POSITIVE LOGITS
     Apparently
    1.46
     According
    1.41
     Presumably
    1.35
     Interestingly
    1.24
     Specifically
    1.24
     Needless
    1.20
     Naturally
    1.20
     However
    1.19
     Though
    1.19
     Sources
    1.19
    Activations Density 0.546%

    No Known Activations