© 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. 6-RES-JB
    11. 14853
    Prev
    Next
    INDEX
    Explanations

    sequences related to legal and public documents, such as terms indicating legal issues, characters, and specific details of legal cases

    oai_token-act-pair · gpt-3.5-turbo

    elements of sports statistics and character traits in fictional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.49
    Newsletter
    -0.48
     Pog
    -0.42
    OIL
    -0.42
    Picture
    -0.40
     Axel
    -0.40
     Dominic
    -0.40
    Nap
    -0.39
     Fake
    -0.39
     bigger
    -0.38
    POSITIVE LOGITS
     respectively
    0.82
    }.
    0.64
    ]).
    0.61
    *.
    0.59
    ]."
    0.59
    anwhile
    0.57
    etheless
    0.54
    >.
    0.53
     eleph
    0.51
    .).
    0.51
    Activations Density 4.970%

    No Known Activations