INDEX

Explanations

specific words related to the term "interactive"

oai_token-act-pair · gpt-3.5-turbo

words related to statuses, conditions, or qualities that end with "-ative."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

owship

-0.95

olicited

-0.93

FORE

-0.78

ortium

-0.77

rir

-0.75

Crash

-0.73

abre

-0.72

ruary

-0.72

ORED

-0.72

mouth

-0.71

POSITIVE LOGITS

ative

0.83

 advers

0.78

 pronoun

0.75

 Powers

0.75

 mating

0.75

 pronouns

0.75

 easing

0.73

 minded

0.72

ptic

0.68

 verbs

0.67

Activations Density 0.084%

specific words related to the term "interactive"

words related to statuses, conditions, or qualities that end with "-ative."

No Comments

No Known Activations