© 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. 2-RES-JB
    11. 24181
    Prev
    Next
    INDEX
    Explanations

    slashes followed by numbers representative of statistical data

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the forward slash character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Syl
    -0.72
     Obi
    -0.70
     creep
    -0.69
     imperson
    -0.67
     Fidel
    -0.67
     Friend
    -0.66
    ļéĨĴ
    -0.66
     Cyrus
    -0.65
     Primordial
    -0.65
     Slug
    -0.64
    POSITIVE LOGITS
    etc
    1.12
    PUT
    1.02
    oct
    0.99
    pmwiki
    0.98
    1000
    0.97
    Flickr
    0.95
    2014
    0.93
    2015
    0.93
    CN
    0.92
    2011
    0.92
    Activations Density 0.077%

    No Known Activations