INDEX

Explanations

the word "supporters" along with interactions or actions associated with supporters

oai_token-act-pair · gpt-3.5-turbo

references to supporters

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

 geological

-0.66

ered

-0.63

PASS

-0.63

abus

-0.62

 delic

-0.61

geon

-0.61

 Injury

-0.60

 Adventures

-0.60

 Surgery

-0.59

puter

-0.59

POSITIVE LOGITS

hesis

1.00

hetical

0.97

hips

0.93

hip

0.86

 supporters

0.83

Supporters

0.83

 Supporters

0.79

 cheering

0.76

yip

0.76

 supporter

0.72

Activations Density 0.024%

the word "supporters" along with interactions or actions associated with supporters

references to supporters

No Comments

No Known Activations