© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15179
    Prev
    Next
    INDEX
    Explanations

    words related to aimlessness or lack of direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "lessly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rite
    -0.77
    Reviewer
    -0.72
    icket
    -0.68
    oplan
    -0.64
    BN
    -0.64
    pillar
    -0.64
    href
    -0.64
    itu
    -0.63
    topic
    -0.63
    RAM
    -0.62
    POSITIVE LOGITS
    theless
    0.91
    atility
    0.77
    lessly
    0.77
    liness
    0.72
    ionage
    0.71
     unaccompanied
    0.69
    lihood
    0.67
    jured
    0.67
    \\\\
    0.66
    icated
    0.65
    Activations Density 0.012%

    No Known Activations