INDEX

Explanations

phrases related to showcasing or presenting something

oai_token-act-pair · gpt-3.5-turbo

instances of displaying or showcasing something

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

unker

-0.85

ignore

-0.76

witch

-0.75

ummer

-0.70

ucket

-0.69

ecause

-0.68

ijn

-0.68

 msec

-0.68

bay

-0.64

ias

-0.64

POSITIVE LOGITS

 talents

0.95

 credentials

0.89

 virtues

0.89

 newest

0.87

 inventions

0.87

 concepts

0.86

 accomplishments

0.85

 ideas

0.82

 PowerPoint

0.76

concept

0.75

Activations Density 0.331%

phrases related to showcasing or presenting something

instances of displaying or showcasing something

No Comments

No Known Activations