INDEX

Explanations

location-based phrases

oai_token-act-pair · gpt-3.5-turbo

references to locations or regional identifiers in contexts such as business or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 analys

-0.79

 behaviour

-0.75

 analyse

-0.74

ongyang

-0.72

 adaptations

-0.70

 composition

-0.70

 behaviours

-0.70

 adaptation

-0.68

 fins

-0.68

 sugg

-0.67

POSITIVE LOGITS

aucuses

1.08

 Klux

0.79

APTER

0.78

edu

0.77

immigrant

0.75

church

0.74

Ohio

0.74

population

0.71

 NAACP

0.71

JR

0.71

Activations Density 0.372%

location-based phrases

references to locations or regional identifiers in contexts such as business or media

No Comments

No Known Activations