INDEX

Explanations

locations or distances from a reference point

oai_token-act-pair · gpt-3.5-turbo

phrases indicating distance or origin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

LC

-0.78

seek

-0.78

BT

-0.77

cn

-0.75

TPPStreamerBot

-0.75

Shift

-0.75

potion

-0.74

frey

-0.73

Ĥª

-0.73

jong

-0.73

POSITIVE LOGITS

 afar

0.98

 whence

0.84

 coast

0.82

 sunrise

0.82

 sunset

0.81

 shore

0.78

 anywhere

0.77

 conception

0.77

 extinction

0.77

 Franch

0.73

Activations Density 0.053%

locations or distances from a reference point

phrases indicating distance or origin

No Comments

No Known Activations