INDEX

Explanations

references to APIs and their related concepts

oai_token-act-pair · gpt-3.5-turbo

references to APIs in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ners

-0.82

pard

-0.79

lihood

-0.78

fur

-0.77

 Cthulhu

-0.76

ning

-0.76

 Gaia

-0.75

bilt

-0.74

creen

-0.74

interest

-0.72

POSITIVE LOGITS

KEN

0.94

 endpoint

0.87

istry

0.87

yip

0.86

API

0.83

API

0.82

hod

0.78

 Token

0.76

 gateway

0.75

ID

0.75

Activations Density 0.009%

references to APIs and their related concepts

references to APIs in technical contexts

No Comments

No Known Activations