INDEX

Explanations

locations or businesses

oai_token-act-pair · gpt-3.5-turbo

references to geographical 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 @ 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

fecture

-0.88

earance

-0.75

attering

-0.69

udence

-0.68

ifice

-0.68

enance

-0.68

glomer

-0.67

ournal

-0.66

ettings

-0.66

itability

-0.65

POSITIVE LOGITS

Wing

0.89

 Creek

0.86

 Grove

0.82

Squ

0.81

 Rider

0.81

 Hill

0.80

 Hawk

0.79

 Valley

0.78

dale

0.77

 Alley

0.76

Activations Density 0.327%

locations or businesses

references to geographical locations or entities

No Comments

No Known Activations