INDEX

Explanations

words related to physical stands or positions

oai_token-act-pair · gpt-3.5-turbo

the word "stand" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

actionDate

-0.90

EStream

-0.80

REDACTED

-0.76

hammad

-0.76

EStreamFrame

-0.73

nesota

-0.70

NetMessage

-0.70

ertodd

-0.69

oleon

-0.68

avascript

-0.68

POSITIVE LOGITS

still

1.31

bys

1.07

ings

0.96

outs

0.94

pipe

0.93

offs

0.86

alone

0.86

atively

0.82

ards

0.81

mount

0.80

Activations Density 0.025%

words related to physical stands or positions

the word "stand" in various contexts

No Comments

No Known Activations