© 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. 21904
    Prev
    Next
    INDEX
    Explanations

    the word "Ter" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ter" in various 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
    issance
    -0.78
    ãģ®éŃĶ
    -0.75
    ãģį
    -0.69
    atform
    -0.68
    ELS
    -0.66
     business
    -0.66
     trout
    -0.66
    unct
    -0.64
     Papua
    -0.63
    ħĭ
    -0.63
    POSITIVE LOGITS
    rible
    1.45
    race
    1.22
    ribly
    1.20
    rors
    1.18
    mite
    1.13
    rance
    1.13
    rence
    1.10
    rier
    1.09
    restrial
    1.08
    mine
    1.08
    Activations Density 0.016%

    No Known Activations