INDEX

Explanations

phrases containing the word "lines"

oai_token-act-pair · gpt-3.5-turbo

references to "lines," particularly in a metaphorical or structural context

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

CVE

-0.93

CLASSIFIED

-0.83

rontal

-0.80

è¦ļéĨĴ

-0.80

 unden

-0.75

PDATE

-0.75

ILLE

-0.73

lisher

-0.73

Instance

-0.73

ILY

-0.72

POSITIVE LOGITS

pace

0.92

lines

0.91

manship

0.86

aments

0.85

 lines

0.84

urgical

0.84

breaks

0.83

 Lines

0.82

mus

0.82

heet

0.77

Activations Density 0.027%

phrases containing the word "lines"

references to "lines," particularly in a metaphorical or structural context

No Comments

No Known Activations