INDEX

Explanations

phrases related to removal or elimination

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "remove" and its variations

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

ingham

-0.72

 msec

-0.71

 Rate

-0.68

matic

-0.64

ERAL

-0.64

rium

-0.62

acebook

-0.62

 Winds

-0.61

zag

-0.60

jah

-0.59

POSITIVE LOGITS

uder

0.86

 unnecessary

0.80

 foreskin

0.75

 redundant

0.75

leted

0.74

 limbs

0.70

 superflu

0.69

cliffe

0.68

 obsolete

0.68

ãĤĵ

0.66

Activations Density 0.043%

phrases related to removal or elimination

occurrences of the word "remove" and its variations

No Comments

No Known Activations