INDEX

Explanations

instances of the word "appear" or its variations

oai_token-act-pair · gpt-3.5-turbo

phrases related to observations or interpretations

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

ests

-0.76

shaw

-0.72

zsche

-0.70

ses

-0.68

fts

-0.67

oller

-0.64

mys

-0.62

milo

-0.61

ulkan

-0.60

aga

-0.60

POSITIVE LOGITS

 poised

0.92

to

0.88

 destined

0.85

 unchanged

0.84

 innocuous

0.77

 Tradable

0.74

 unstoppable

0.72

 prominently

0.72

 anomal

0.69

 unlikely

0.69

Activations Density 0.037%

instances of the word "appear" or its variations

phrases related to observations or interpretations

No Comments

No Known Activations