© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9762
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or evidence

    oai_token-act-pair · gpt-3.5-turbo

    the concept of support or endorsement, particularly in the context of evidence or authority

    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
    nel
    -0.69
    anny
    -0.69
    ities
    -0.68
    urious
    -0.68
    anooga
    -0.65
     Hots
    -0.64
    entric
    -0.64
    inational
    -0.64
    alde
    -0.63
     newsp
    -0.62
    POSITIVE LOGITS
    track
    0.84
    taking
    0.79
    steen
    0.77
    ups
    0.74
    hard
    0.74
    abies
    0.73
    swing
    0.72
    raise
    0.72
    drive
    0.72
    GROUND
    0.70
    Activations Density 0.032%

    No Known Activations