INDEX

Explanations

mentions of the sports team "Detroit Red Wings"

oai_token-act-pair · gpt-3.5-turbo

mentions of the "Wings," specifically in relation to the Detroit Red Wings hockey team

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

anyahu

-0.89

yss

-0.74

ctica

-0.73

izabeth

-0.66

abin

-0.64

ouple

-0.63

autical

-0.63

uments

-0.63

tery

-0.62

acci

-0.62

POSITIVE LOGITS

 Wings

0.95

hip

0.84

pan

0.82

pread

0.77

layer

0.75

 Tigers

0.73

 maiden

0.73

ski

0.73

warm

0.72

nuts

0.71

Activations Density 0.021%

mentions of the sports team "Detroit Red Wings"

mentions of the "Wings," specifically in relation to the Detroit Red Wings hockey team

No Comments

No Known Activations