© 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. 4464
    Prev
    Next
    INDEX
    Explanations

    mentions of the journalist Amy Goodman

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named "Amy Goodman" and related organizations or entities

    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
    angers
    -0.76
    esville
    -0.72
    stood
    -0.70
    etime
    -0.68
     virginity
    -0.65
    ties
    -0.64
    adal
    -0.64
    reek
    -0.64
    bent
    -0.61
    cise
    -0.61
    POSITIVE LOGITS
     GOODMAN
    1.92
    AMY
    1.10
    APH
    1.01
    ICAN
    0.84
    gdala
    0.83
    CLASSIFIED
    0.83
     Doodle
    0.82
    NER
    0.79
    ANK
    0.79
    JP
    0.77
    Activations Density 0.009%

    No Known Activations