© 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. 5299
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially involved in a legal issue

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or characters associated with specific activities or roles, particularly in a film or narrative context

    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
    ailability
    -0.85
    ©¶æ¥µ
    -0.79
    cffff
    -0.79
     mathemat
    -0.77
    eatures
    -0.72
     metic
    -0.71
    ements
    -0.69
    etheless
    -0.69
     confir
    -0.69
     conflic
    -0.69
    POSITIVE LOGITS
    )].
    0.77
    +)
    0.74
    ))))
    0.72
    ]);
    0.72
     Jr
    0.70
     tears
    0.68
    )))
    0.64
    )...
    0.64
     />
    0.62
    "/>
    0.62
    Activations Density 0.087%

    No Known Activations