© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    phrases ending in a specific punctuation mark (".") signifying the end of a statement or sentence

    oai_token-act-pair · gpt-3.5-turbo

    the presence of sentence-ending punctuation marks

    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
     contrace
    -0.80
     experien
    -0.73
     segreg
    -0.72
     locality
    -0.68
     confir
    -0.68
     grades
    -0.67
     challeng
    -0.65
     consumed
    -0.65
     transitions
    -0.65
     neighb
    -0.65
    POSITIVE LOGITS
     âĢķ
    0.93
    >>\
    0.82
    Enlarge
    0.72
     ["
    0.71
    soType
    0.69
    Premium
    0.68
     Translation
    0.68
    externalActionCode
    0.68
    wav
    0.67
     Statements
    0.66
    Activations Density 0.062%

    No Known Activations