INDEX

Explanations

statements or claims of fact

oai_token-act-pair · gpt-3.5-turbo

words related 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

İĭ

-0.80

 throats

-0.76

gian

-0.69

 veins

-0.69

 charcoal

-0.68

 Hutchinson

-0.68

haw

-0.67

 eyebrows

-0.66

DER

-0.66

 Bhar

-0.65

POSITIVE LOGITS

Fact

1.06

ional

0.87

 Fact

0.83

fact

0.83

facts

0.81

itious

0.80

ual

0.78

ulence

0.77

onom

0.77

finding

0.75

Activations Density 0.008%

statements or claims of fact

words related to factual statements or claims

No Comments

No Known Activations