© 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. 7-RES-JB
    11. 10044
    Prev
    Next
    INDEX
    Explanations

    written text that includes the word "Ter" followed by various suffixes which are common in personal names such as "ner", "rence", and "ry"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.71
     inclusive
    -0.70
    ãģį
    -0.70
    issance
    -0.68
     trout
    -0.67
    ħĭ
    -0.66
     business
    -0.66
     Upton
    -0.65
     disparate
    -0.65
    ELS
    -0.63
    POSITIVE LOGITS
    rible
    1.51
    race
    1.29
    ribly
    1.25
    rance
    1.18
    rors
    1.18
    mite
    1.17
    restrial
    1.16
    rell
    1.15
    rence
    1.12
    abytes
    1.08
    Activations Density 0.024%

    No Known Activations