© 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. 11-RES-JB
    11. 17199
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating the topic of discussion or debate

    oai_token-act-pair · gpt-3.5-turbo

    phrases and positions related to political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intend
    -0.86
    ractor
    -0.81
    phia
    -0.77
    agues
    -0.77
    stro
    -0.76
    esters
    -0.73
    externalActionCode
    -0.71
    semble
    -0.71
    issance
    -0.70
    ographers
    -0.69
    POSITIVE LOGITS
     abortion
    1.22
     immigration
    1.18
     homosexuality
    1.16
     issues
    1.14
     taxation
    1.13
     sexuality
    1.09
     matters
    1.07
     morality
    1.01
     topics
    1.00
     contraception
    0.99
    Activations Density 0.182%

    No Known Activations