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. 6-RES-JB
    6. 19479
    Prev
    Next
    INDEX
    Explanations

    phrases related to universal themes or general statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of collective sentiment or shared experiences among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qus
    -0.69
    edia
    -0.65
    ahime
    -0.64
    claw
    -0.62
    pelling
    -0.62
    rer
    -0.62
    vernment
    -0.61
    eln
    -0.59
     Advertisement
    -0.59
     angered
    -0.58
    POSITIVE LOGITS
     except
    1.16
     imaginable
    0.95
    Tes
    0.92
    except
    0.92
     equally
    0.89
     alike
    0.76
    winner
    0.72
     interchangeable
    0.71
     conceivable
    0.71
    ãĤ«
    0.65
    Activations Density 0.293%

    No Known Activations