INDEX

Explanations

speculations or suggestions

oai_token-act-pair · gpt-3.5-turbo

verbs and actions related to suggestions and acceptance

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

Downloadha

-0.81

creen

-0.77

avorite

-0.77

apter

-0.64

ULTS

-0.63

ggle

-0.63

wife

-0.63

USD

-0.63

quo

-0.61

 awake

-0.59

POSITIVE LOGITS

ed

2.30

ing

1.69

edIn

1.49

edly

1.44

ered

1.27

ers

1.15

ation

1.12

edin

1.11

er

1.11

eds

1.08

Activations Density 0.172%

speculations or suggestions

verbs and actions related to suggestions and acceptance

No Comments

No Known Activations