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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 3293
    Prev
    Next
    INDEX
    Explanations

    phrases referring to actions or characteristics done individually

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to autonomy and independence

    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
    obar
    -0.81
    recated
    -0.81
    mers
    -0.79
    anwhile
    -0.75
    olic
    -0.74
    gerald
    -0.71
    osi
    -0.68
    ————————
    -0.68
    thouse
    -0.67
    amac
    -0.67
    POSITIVE LOGITS
     accord
    0.92
    Cloud
    0.84
     backyard
    0.76
     footing
    0.73
     merits
    0.70
     detriment
    0.70
     initiative
    0.69
     hands
    0.68
     turf
    0.65
     discretion
    0.64
    Activations Density 0.034%

    No Known Activations