INDEX

Explanations

mentions of strength or intensity

oai_token-act-pair · gpt-3.5-turbo

Repeated instances of the word "strong" 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 @ 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

oleon

-0.75

 unfocusedRange

-0.72

 Newly

-0.72

regon

-0.71

 Correction

-0.70

 Sloan

-0.68

 Wonderland

-0.66

ilege

-0.66

Ì¶

-0.64

 Hebdo

-0.63

POSITIVE LOGITS

 believer

0.88

nesses

0.86

man

0.85

 circumst

0.84

 enough

0.84

arm

0.83

 proponent

0.83

enough

0.81

 deterrent

0.81

 indication

0.81

Activations Density 0.061%

mentions of strength or intensity

Repeated instances of the word "strong" in various contexts

No Comments

No Known Activations