© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to "matter" in legal or procedural contexts

    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
    ãĥ³ãĤ¸
    -0.84
    OWN
    -0.77
    ãĥ¼ãĥĨ
    -0.70
    aez
    -0.70
    ARP
    -0.69
    NetMessage
    -0.67
    eele
    -0.65
    DIT
    -0.64
    adena
    -0.64
    phia
    -0.64
    POSITIVE LOGITS
     pertaining
    0.99
     relating
    0.89
     matter
    0.84
     surrounding
    0.82
    ional
    0.82
     matters
    0.79
     involving
    0.79
     resolved
    0.75
    matter
    0.75
     concerning
    0.75
    Activations Density 0.035%

    No Known Activations