INDEX

Explanations

locations or entities related to the color blue

oai_token-act-pair · gpt-3.5-turbo

references to the color blue or entities associated with the term "blue."

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

Ö¼

-0.94

ROR

-0.84

NRS

-0.82

uador

-0.82

rolet

-0.78

 srfAttach

-0.75

IPM

-0.74

ITED

-0.73

IFA

-0.73

ernandez

-0.73

POSITIVE LOGITS

prints

1.35

grass

1.32

berry

1.17

bird

0.97

 ribbon

0.95

beard

0.90

 Ribbon

0.89

berries

0.88

fin

0.82

irection

0.82

Activations Density 0.018%

locations or entities related to the color blue

references to the color blue or entities associated with the term "blue."

No Comments

No Known Activations