INDEX

Explanations

specific instances where an entity states its actions or plans

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "it" followed by auxiliary verbs indicating various states or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 charisma

-0.70

 Conquest

-0.68

 trivia

-0.64

 vanity

-0.61

stead

-0.60

TED

-0.60

 Mens

-0.60

 Asgard

-0.60

Ent

-0.58

POSITIVE LOGITS

 regretted

0.89

 notified

0.84

 intends

0.84

©¶æ

0.82

 reached

0.81

 encount

0.79

 expects

0.79

 received

0.78

 honoured

0.76

 intend

0.75

Activations Density 0.134%

specific instances where an entity states its actions or plans

instances of the pronoun "it" followed by auxiliary verbs indicating various states or actions

No Comments

No Known Activations