INDEX

Explanations

phrases asking questions or seeking explanations

oai_token-act-pair · gpt-3.5-turbo

phrases that express uncertainty or questions about various topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĿ

-0.73

letter

-0.66

vik

-0.66

 Nurs

-0.64

sectional

-0.64

rief

-0.63

bley

-0.63

Joy

-0.62

IST

-0.61

cells

-0.61

POSITIVE LOGITS

why

1.01

 whether

0.89

how

0.87

WHY

0.81

 date

0.77

 whereabouts

0.74

yx

0.74

 justify

0.73

 ascertain

0.68

ingu

0.67

Activations Density 0.026%

phrases asking questions or seeking explanations

phrases that express uncertainty or questions about various topics

No Comments

No Known Activations