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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 9736
    Prev
    Next
    INDEX
    Explanations

    names of people or entities along with a verb indicating action

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its variations indicating status or existence

    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
    itiveness
    -0.68
    iates
    -0.61
    ear
    -0.59
    )).
    -0.58
    —"
    -0.57
    rouse
    -0.56
     latch
    -0.55
     entails
    -0.54
    role
    -0.54
    catch
    -0.53
    POSITIVE LOGITS
    senal
    0.95
     hereby
    0.79
     awarded
    0.75
     rumored
    0.74
     indeed
    0.70
     not
    0.67
    cussion
    0.67
     listed
    0.67
     NOT
    0.66
     also
    0.65
    Activations Density 1.225%

    No Known Activations