INDEX

Explanations

phrases related to proving something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "prove" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

phrine

-0.73

srf

-0.69

ufact

-0.65

cious

-0.65

atching

-0.64

assisted

-0.64

ilver

-0.63

itching

-0.62

 Returning

-0.61

 Surv

-0.61

POSITIVE LOGITS

 prove

1.07

 proves

0.97

 proving

0.85

 proved

0.80

 dispro

0.79

ãĥĺ

0.77

uably

0.76

 proofs

0.75

ĸļ

0.75

iary

0.74

Activations Density 0.007%

phrases related to proving something

occurrences of the word "prove" in various contexts

No Comments

No Known Activations