© 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. 23991
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are described or mentioned in association with something else

    oai_token-act-pair · gpt-3.5-turbo

    the word "alongside" and its associated context

    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
    chin
    -0.74
    asse
    -0.71
    nery
    -0.69
    itar
    -0.68
    ek
    -0.68
    eln
    -0.67
    apego
    -0.66
    iencies
    -0.66
     lockout
    -0.66
    cas
    -0.65
    POSITIVE LOGITS
    ÃįÃį
    0.87
    lihood
    0.87
     alongside
    0.86
     Sakuya
    0.84
    side
    0.83
    ngth
    0.71
     Nico
    0.68
     Dame
    0.67
    ãĤ´ãĥ³
    0.64
    standing
    0.63
    Activations Density 0.008%

    No Known Activations