© 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. 6-RES-JB
    11. 18449
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions and qualifications in a process or event

    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
    toggle
    -0.78
    fter
    -0.76
    picture
    -0.67
    guide
    -0.67
     LOT
    -0.64
     Shots
    -0.63
    ][/
    -0.62
    photo
    -0.60
    ggles
    -0.60
    gery
    -0.60
    POSITIVE LOGITS
     raining
    1.01
     interven
    0.68
    unes
    0.66
     ratified
    0.65
     costs
    0.65
    rodu
    0.65
     impossible
    0.64
     predecessor
    0.63
     reopened
    0.62
     itself
    0.62
    Activations Density 0.639%

    No Known Activations