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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19785
    Prev
    Next
    INDEX
    Explanations

    actions related to presenting, generating, and raising various topics or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing events or developments

    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
    aurus
    -0.69
     Guan
    -0.65
    pun
    -0.64
    estate
    -0.61
     Athletic
    -0.61
     Mercenary
    -0.60
     Beg
    -0.59
     hosp
    -0.57
     Scorp
    -0.56
     occupancy
    -0.56
    POSITIVE LOGITS
    osate
    1.03
    20439
    0.88
    olkien
    0.73
    Attach
    0.73
    pdf
    0.71
     aired
    0.70
    EGIN
    0.68
    Dispatch
    0.66
    ĸļ
    0.66
    essler
    0.66
    Activations Density 0.790%

    No Known Activations