© 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. 2-RES-JB
    11. 951
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "orted"

    oai_token-act-pair · gpt-4-turbo

    phrases related to demanding or urging action

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "extort" and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.81
    Ü
    -0.78
    opens
    -0.74
     semif
    -0.71
    irc
    -0.69
    pi
    -0.67
    ellen
    -0.64
     newcom
    -0.62
    pton
    -0.62
     Stadium
    -0.61
    POSITIVE LOGITS
    ort
    0.85
    orted
    0.83
    orts
    0.77
    orting
    0.76
    ions
    0.75
    irect
    0.75
    tery
    0.73
    ingly
    0.72
    urous
    0.69
    lessly
    0.69
    Activations Density 0.014%

    No Known Activations