INDEX

Explanations

phrases related to locations or physical directions

oai_token-act-pair · gpt-3.5-turbo

references to off-campus activities and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

SPONSORED

-0.85

pton

-0.79

éĹĺ

-0.74

ancial

-0.68

acci

-0.68

estine

-0.66

Maria

-0.65

apest

-0.64

illac

-0.64

ilver

-0.63

POSITIVE LOGITS

 seams

0.72

fen

0.71

 contrace

0.70

 coasts

0.69

 tang

0.69

 shores

0.69

stretched

0.67

 territory

0.65

 stroke

0.64

 Galile

0.64

Activations Density 0.178%

phrases related to locations or physical directions

references to off-campus activities and events

No Comments

No Known Activations