INDEX

Explanations

words containing the substring "rop" with varying levels of intensity

oai_token-act-pair · gpt-3.5-turbo

references to 'tropical' and 'subtropical' environments

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

CLE

-0.69

 Sins

-0.66

BIP

-0.62

hart

-0.61

irements

-0.60

$$

-0.60

 eminent

-0.60

 defensively

-0.59

sar

-0.59

auga

-0.59

POSITIVE LOGITS

oulos

1.39

hedon

1.35

rop

0.98

hens

0.95

ower

0.95

onent

0.94

ods

0.89

hen

0.88

olitics

0.84

eli

0.83

Activations Density 0.018%

words containing the substring "rop" with varying levels of intensity

references to 'tropical' and 'subtropical' environments

No Comments

No Known Activations