INDEX

Explanations

phrases related to completion or accomplishment

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 @ 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

RAD

-0.71

 guiActiveUnfocused

-0.69

osate

-0.67

 swept

-0.65

Pom

-0.62

 continuum

-0.62

 Mutant

-0.62

 Mour

-0.60

Nib

-0.60

 Golem

-0.60

POSITIVE LOGITS

yet

0.87

_>

0.86

âģ

0.85

âĢķ

0.85

£

0.85

Ì

0.82

¦

0.81

¹

0.81

evil

0.80

Ĭ

0.80

Activations Density 0.170%

phrases related to completion or accomplishment

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

No Comments

No Known Activations