© 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. 4-RES-JB
    11. 14880
    Prev
    Next
    INDEX
    Explanations

    phrases related to sensory experiences, particularly with a focus on auditory and visual elements

    oai_token-act-pair · gpt-3.5-turbo

    elements that convey strong emotional textures or atmospheres in artistic works

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

    No Comments

    Negative Logits
     Experts
    -0.81
    igham
    -0.81
    osponsors
    -0.80
    mbudsman
    -0.78
    çİĭ
    -0.77
    Testing
    -0.76
     Applicant
    -0.76
     Commissioners
    -0.76
     Prosecut
    -0.75
    Council
    -0.75
    POSITIVE LOGITS
     melanch
    1.19
     rhythms
    1.06
     poetic
    1.02
     themes
    1.01
     melancholy
    0.99
     poetry
    0.98
     lyr
    0.98
     tunes
    0.96
     melodies
    0.95
     vocals
    0.93
    Activations Density 0.371%

    No Known Activations