INDEX

Explanations

pairs of names

oai_token-act-pair · gpt-3.5-turbo

the connective "and" 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

éŃĶ

-0.71

cms

-0.69

physical

-0.66

Physical

-0.66

matter

-0.65

Requirements

-0.64

note

-0.64

SOURCE

-0.63

currency

-0.63

Versions

-0.63

POSITIVE LOGITS

 Associates

1.05

 Sons

1.01

ERSON

0.87

 others

0.84

 colleagues

0.81

 vice

0.74

 assorted

0.71

his

0.70

 associates

0.70

axter

0.69

Activations Density 0.187%

pairs of names

the connective "and" in various contexts

No Comments

No Known Activations