INDEX

Explanations

statements that are presented as facts

oai_token-act-pair · gpt-3.5-turbo

references to factual statements or claims

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

avorite

-0.79

 Klux

-0.79

jri

-0.76

isoft

-0.71

artney

-0.69

ModLoader

-0.69

interstitial

-0.69

ctic

-0.68

hod

-0.68

 Carbuncle

-0.67

POSITIVE LOGITS

ually

1.26

orial

1.15

itious

1.05

ional

1.03

oids

0.99

ially

0.94

uality

0.92

ual

0.91

oid

0.88

icity

0.86

Activations Density 0.029%

statements that are presented as facts

references to factual statements or claims

No Comments

No Known Activations