INDEX

Explanations

phrases related to beginnings or starting points

oai_token-act-pair · gpt-3.5-turbo

phrases that suggest beginnings, introductions, or first occurrences

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

ult

-0.75

luaj

-0.67

 Difficulty

-0.66

laws

-0.66

isl

-0.65

-0.61

sleep

-0.61

leigh

-0.60

inance

-0.60

phasis

-0.59

POSITIVE LOGITS

 cents

0.87

 placeholder

0.75

 prelim

0.75

 sympt

0.73

 collateral

0.71

 scratching

0.69

ifiable

0.65

 anecdotal

0.65

 salv

0.63

 scratched

0.63

Activations Density 0.171%

phrases related to beginnings or starting points

phrases that suggest beginnings, introductions, or first occurrences

No Comments

No Known Activations