INDEX

Explanations

terms related to automotive features and parts

oai_token-act-pair · gpt-3.5-turbo

terms related to anatomical structures or compartments, especially glands and hatches

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

guyen

-0.81

ocre

-0.79

iter

-0.78

velength

-0.78

fing

-0.76

esty

-0.75

ilver

-0.74

udging

-0.73

itivity

-0.72

pez

-0.72

POSITIVE LOGITS

allic

0.74

otle

0.73

 Mansion

0.72

 Clicker

0.70

arding

0.69

rics

0.69

ARD

0.69

ULAR

0.68

Rae

0.68

lain

0.67

Activations Density 0.040%

terms related to automotive features and parts

terms related to anatomical structures or compartments, especially glands and hatches

No Comments

No Known Activations