INDEX

Explanations

instances where something is visually demonstrated or displayed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "shown" referencing observations or displays

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

entric

-0.79

alez

-0.74

claimer

-0.69

lly

-0.67

idian

-0.66

iding

-0.65

pex

-0.65

ettlement

-0.63

etheless

-0.62

pton

-0.61

POSITIVE LOGITS

ered

1.00

runners

0.92

¶æ

0.86

rooms

0.83

 Thumbnails

0.83

 flashes

0.79

otes

0.75

biz

0.74

Haunted

0.74

Ò

0.71

Activations Density 0.041%

instances where something is visually demonstrated or displayed

instances of the word "shown" referencing observations or displays

No Comments

No Known Activations