INDEX

Explanations

phrases indicating a shift in focus or attention

oai_token-act-pair · gpt-3.5-turbo

phrases indicating personal experiences and reflections

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

staking

-0.77

tm

-0.72

uum

-0.69

natal

-0.69

rique

-0.65

emort

-0.65

etheless

-0.64

liness

-0.64

fine

-0.64

zinski

-0.64

POSITIVE LOGITS

 Spiel

0.66

 laps

0.59

ulic

0.57

 ripe

0.57

attery

0.57

rawdownloadcloneembedreportprint

0.56

quickShipAvailable

0.56

 again

0.55

 boarded

0.54

 corrected

0.54

Activations Density 0.119%

phrases indicating a shift in focus or attention

phrases indicating personal experiences and reflections

No Comments

No Known Activations