INDEX

Explanations

comparisons between different things or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate certainty or the assertion of facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Chamberlain

-0.57

umbn

-0.55

airo

-0.52

hoff

-0.51

Watch

-0.50

åĳ

-0.50

 onlook

-0.50

ioch

-0.49

aires

-0.49

ourt

-0.49

POSITIVE LOGITS

 impossible

1.09

 untrue

0.96

 impractical

0.94

 useless

0.93

 feasible

0.91

omorphic

0.91

 advisable

0.91

 possible

0.90

 unus

0.90

 irrelevant

0.88

Activations Density 0.335%

comparisons between different things or situations

phrases that indicate certainty or the assertion of facts

No Comments

No Known Activations