Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3766
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to locations, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric identifiers or names associated with iconic brands or media entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     omission
    -0.67
    OWS
    -0.63
     Trafford
    -0.62
    DN
    -0.61
     disenfranch
    -0.60
     Remain
    -0.59
     Pages
    -0.59
     wolf
    -0.58
     Dane
    -0.57
    #$
    -0.56
    POSITIVE LOGITS
    monary
    0.98
    irie
    0.92
    etic
    0.88
    odic
    0.85
    incial
    0.84
    oe
    0.84
    ilon
    0.84
    ocry
    0.83
    perty
    0.82
    ophe
    0.79
    Activations Density 0.129%

    No Known Activations