INDEX

Explanations

keywords related to agreements or compromises, often involving concessions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "concession."

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

nan

-0.68

opes

-0.62

psc

-0.62

chem

-0.61

nin

-0.61

 Lyme

-0.60

²¾

-0.60

ross

-0.60

mind

-0.59

energy

-0.59

POSITIVE LOGITS

 concessions

1.19

 concession

1.09

ļéĨĴ

0.87

aires

0.84

 bargain

0.78

aire

0.78

cession

0.76

ensical

0.75

 amnesty

0.75

serv

0.73

Activations Density 0.027%

keywords related to agreements or compromises, often involving concessions

instances of the word "concession."

No Comments

No Known Activations