INDEX

Explanations

phrases or sentences that include the word 'bit'

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "bit," indicating a focus on incremental changes or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ammad

-0.82

¥µ

-0.78

 pend

-0.70

idth

-0.70

veyard

-0.65

ADRA

-0.65

etheus

-0.65

ateful

-0.64

èĢħ

-0.64

yout

-0.63

POSITIVE LOGITS

umen

1.13

terness

1.02

meal

0.99

umin

0.94

wig

0.92

buck

0.92

ches

0.90

reet

0.89

ching

0.87

maps

0.86

Activations Density 0.018%

phrases or sentences that include the word 'bit'

phrases that include the word "bit," indicating a focus on incremental changes or assessments

No Comments

No Known Activations