INDEX

Explanations

proper nouns related to different locations or entities

oai_token-act-pair · gpt-3.5-turbo

references to places and geographical locations

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

Filename

-0.78

=-=-=-=-

-0.75

kefeller

-0.75

 magnification

-0.71

 IMAGES

-0.69

 VIDEOS

-0.69

\/\/

-0.68

 Uriel

-0.65

NCT

-0.65

 GEAR

-0.63

POSITIVE LOGITS

pard

0.82

pole

0.80

stad

0.78

anty

0.74

peria

0.74

arde

0.74

lehem

0.72

igham

0.71

illance

0.70

conn

0.70

Activations Density 0.067%

proper nouns related to different locations or entities

references to places and geographical locations

No Comments

No Known Activations