© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11803
    Prev
    Next
    INDEX
    Explanations

    phrases or fragments related to online sharing or commentary, potentially featuring the pronoun 'we'

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "we" indicating a collective perspective or group involvement

    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
    ional
    -0.76
    uses
    -0.75
    ion
    -0.72
    ioned
    -0.72
    netflix
    -0.68
    jury
    -0.68
    uten
    -0.67
    ussen
    -0.66
    life
    -0.66
    imeter
    -0.65
    POSITIVE LOGITS
    IRD
    1.21
    ALTH
    1.16
    WE
    1.13
    LL
    1.11
    YC
    1.08
    VER
    1.07
    BRE
    1.03
    ETS
    1.02
    VE
    1.01
    PLAY
    1.00
    Activations Density 0.014%

    No Known Activations