© 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. 10-RES-JB
    11. 14018
    Prev
    Next
    INDEX
    Explanations

    legal terms and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sustainability
    -0.87
     localized
    -0.83
     dips
    -0.82
     enthusi
    -0.79
     welcome
    -0.79
     sustainable
    -0.79
     nostalg
    -0.78
     spreads
    -0.77
     percept
    -0.77
     humour
    -0.76
    POSITIVE LOGITS
    Prosecutors
    1.87
     Prosecutors
    1.83
    Judge
    1.74
    Prosecut
    1.68
    Court
    1.63
     Judge
    1.41
    Attorney
    1.37
     Charges
    1.37
     Prosecutor
    1.34
    Investigators
    1.33
    Activations Density 0.290%

    No Known Activations