INDEX

Explanations

locations or entities related to a specific geographical region

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Phys

-1.00

bleacher

-0.81

 Wally

-0.79

Sym

-0.74

Legendary

-0.72

raviolet

-0.72

TABLE

-0.71

ships

-0.71

Scient

-0.71

 Mortal

-0.71

POSITIVE LOGITS

 dictatorship

1.00

 regime

0.96

 dictator

0.92

 bloc

0.89

 nationalist

0.88

 confiscated

0.84

 govern

0.84

 communist

0.82

 detained

0.80

 amnesty

0.79

Activations Density 0.705%

locations or entities related to a specific geographical region

references to specific geographic locations or entities

No Comments

No Known Activations