© 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. 7-RES-JB
    11. 24209
    Prev
    Next
    INDEX
    Explanations

    references to activities happening both online and offline

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating activity or engagement in both online and offline contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.76
    erest
    -0.76
    udence
    -0.74
    addafi
    -0.72
    iev
    -0.71
    ato
    -0.66
     Rebell
    -0.66
    akuya
    -0.66
    heim
    -0.65
     Growth
    -0.64
    POSITIVE LOGITS
    izont
    0.81
     absentee
    0.81
     remotely
    0.79
     offline
    0.78
    orld
    0.75
     tele
    0.75
     accessible
    0.75
     indoors
    0.74
     interstate
    0.74
    fax
    0.74
    Activations Density 0.302%

    No Known Activations