© 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. 4-RES-JB
    11. 15216
    Prev
    Next
    INDEX
    Explanations

    words starting with the letter 't' followed by another letter

    oai_token-act-pair · gpt-3.5-turbo

    the letter 't' at varying instances

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

    No Comments

    Negative Logits
    éĹĺ
    -0.77
     destro
    -0.76
    Downloadha
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    76561
    -0.69
    EStream
    -0.67
     è£ıè
    -0.67
    ãĤŃ
    -0.67
    CVE
    -0.67
     condem
    -0.66
    POSITIVE LOGITS
    agged
    1.19
    ributes
    1.19
    umbling
    1.19
    ipper
    1.16
    umbled
    1.15
    ucked
    1.15
    agging
    1.15
    ourn
    1.13
    rolled
    1.13
    rolley
    1.12
    Activations Density 0.021%

    No Known Activations