© 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. 21434
    Prev
    Next
    INDEX
    Explanations

    phrases related to frequency or intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "too often" 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
     Sever
    -0.83
     1886
    -0.69
     Revel
    -0.67
    orthy
    -0.65
    joining
    -0.65
    square
    -0.65
    edit
    -0.64
     Levant
    -0.62
     Hess
    -0.62
     Amir
    -0.62
    POSITIVE LOGITS
     misconceptions
    1.11
    Myth
    1.02
     precon
    1.02
     stereotypes
    1.00
    oliberal
    1.00
     clich
    0.98
     myths
    0.96
     stigma
    0.95
     stereotype
    0.93
     outdated
    0.93
    Activations Density 1.330%

    No Known Activations