INDEX

Explanations

words related to evidence or proof

oai_token-act-pair · gpt-3.5-turbo

references to evidence in various contexts

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

•Evidence

No Comments

Negative Logits

skill

-0.76

noxious

-0.72

ija

-0.70

sf

-0.68

frey

-0.68

nas

-0.67

oos

-0.67

sie

-0.63

jc

-0.62

bum

-0.62

POSITIVE LOGITS

 evidence

1.12

evidence

1.11

 Evidence

1.08

Evidence

0.96

 evid

0.89

 proofs

0.79

 proof

0.78

 validity

0.78

edly

0.77

proof

0.72

Activations Density 0.023%

words related to evidence or proof

references to evidence in various contexts

No Comments

No Known Activations