INDEX

Explanations

references to chicken

oai_token-act-pair · gpt-3.5-turbo

references to chicken

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

orsche

-0.87

INAL

-0.81

aylor

-0.78

raints

-0.76

 Palestin

-0.74

oppable

-0.73

ibel

-0.72

unci

-0.72

DPR

-0.72

ilities

-0.71

POSITIVE LOGITS

pox

1.16

 breasts

0.95

meat

0.94

 manure

0.92

fish

0.91

bones

0.91

 thighs

0.89

 chickens

0.85

 wings

0.85

bone

0.84

Activations Density 0.015%

references to chicken

references to chicken

No Comments

No Known Activations