INDEX

Explanations

phrases related to claims or allegations

oai_token-act-pair · gpt-3.5-turbo

terms related to allegations and 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

NetMessage

-1.04

pace

-0.89

everal

-0.80

ockets

-0.77

hops

-0.76

ilver

-0.75

cale

-0.75

cape

-0.73

poons

-0.72

paces

-0.71

POSITIVE LOGITS

lessly

0.84

 refrain

0.83

ariat

0.80

less

0.80

naires

0.78

naire

0.78

 disclaimer

0.77

 count

0.77

lessness

0.77

ously

0.75

Activations Density 0.154%

phrases related to claims or allegations

terms related to allegations and claims

No Comments

No Known Activations