INDEX

Explanations

phrases related to failure or disappointment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "bust" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

THER

-0.80

MAL

-0.71

asonable

-0.69

velength

-0.67

PLAY

-0.65

viron

-0.64

nsic

-0.64

mble

-0.61

onsense

-0.60

IFE

-0.59

POSITIVE LOGITS

 bust

1.37

 Bust

1.03

buster

0.88

outs

0.76

endor

0.74

bowl

0.73

aign

0.72

enance

0.72

ing

0.72

height

0.72

Activations Density 0.006%

phrases related to failure or disappointment

instances of the word "bust" and its variations

No Comments

No Known Activations