INDEX

Explanations

contractions where the subject omits a letter

oai_token-act-pair · gpt-3.5-turbo

instances of the word "didn't" in various contexts

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

 Dise

-0.73

 protected

-0.66

armed

-0.66

 DRAGON

-0.64

 Duty

-0.62

 Casting

-0.62

fields

-0.62

Introduced

-0.61

upp

-0.59

manship

-0.58

POSITIVE LOGITS

't

1.25

etsk

0.90

okia

0.90

nt

0.79

geon

0.78

ger

0.78

ÃŃ

0.76

gered

0.76

":"/

0.75

ned

0.74

Activations Density 0.057%

contractions where the subject omits a letter

instances of the word "didn't" in various contexts

No Comments

No Known Activations