INDEX

Explanations

verbs related to perception or judgment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "seem" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

venge

-0.78

cise

-0.74

 Industry

-0.69

arter

-0.69

prem

-0.69

cised

-0.68

estern

-0.66

EStreamFrame

-0.66

cision

-0.65

cum

-0.65

POSITIVE LOGITS

rils

0.98

Magikarp

0.93

INGS

0.89

lihood

0.82

Wheel

0.81

ĸļ

0.81

\\\\\\\\

0.79

ings

0.74

wip

0.72

DEV

0.71

Activations Density 0.023%

verbs related to perception or judgment

instances of the word "seem" in various contexts

No Comments

No Known Activations