INDEX

Explanations

locations within a building, particularly referring to walls

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "of" 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

Ô

-0.77

inctions

-0.76

arily

-0.75

isoft

-0.73

;;;;;;;;;;;;

-0.72

Äĩ

-0.72

NetMessage

-0.71

 capitalize

-0.71

Ã±

-0.71

jing

-0.70

POSITIVE LOGITS

 Dover

0.71

 course

0.69

JP

0.65

cone

0.64

 Generation

0.63

 Scand

0.63

 Notre

0.62

 inhabited

0.61

Vit

0.61

 Nord

0.60

Activations Density 0.162%

locations within a building, particularly referring to walls

phrases that include the word "of" in various contexts

No Comments

No Known Activations