INDEX

Explanations

phrases related to confirmation or denial

oai_token-act-pair · gpt-3.5-turbo

coordinating conjunctions that connect multiple ideas or clauses in a sentence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Downloadha

-0.73

Magikarp

-0.69

lav

-0.69

hov

-0.69

warm

-0.68

earable

-0.68

BALL

-0.66

 toget

-0.65

NetMessage

-0.63

UGH

-0.63

POSITIVE LOGITS

 Authorities

0.65

eller

0.63

 forgiven

0.61

 apology

0.61

 fals

0.58

 Testament

0.58

 deny

0.57

 distinction

0.57

 omission

0.57

 Vice

0.57

Activations Density 0.195%

phrases related to confirmation or denial

coordinating conjunctions that connect multiple ideas or clauses in a sentence

No Comments

No Known Activations