INDEX

Explanations

questions related to different topics and seeking information

oai_token-act-pair · gpt-3.5-turbo

phrases beginning with "what's" or related interrogative contexts that seek information or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ornings

-0.98

mares

-0.89

adoes

-0.88

chairs

-0.83

aunts

-0.83

classes

-0.82

cles

-0.82

drops

-0.82

runs

-0.80

runners

-0.78

POSITIVE LOGITS

 difference

1.19

 significance

1.17

 Difference

1.02

 likelihood

1.02

 rationale

0.97

 implication

0.96

 relationship

0.94

 relevance

0.94

 meaning

0.94

 reperc

0.93

Activations Density 0.049%

questions related to different topics and seeking information

phrases beginning with "what's" or related interrogative contexts that seek information or clarification

No Comments

No Known Activations