INDEX

Explanations

phrases related to comparison or different aspects of something

oai_token-act-pair · gpt-3.5-turbo

expressions of multiple interpretations or perspectives on a topic

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

bart

-0.66

tailed

-0.63

andel

-0.62

alsa

-0.61

ctors

-0.61

perty

-0.61

prus

-0.60

lish

-0.60

multiple

-0.59

mins

-0.59

POSITIVE LOGITS

 resembles

0.75

 analogous

0.72

 resembling

0.71

0.68

 reminiscent

0.68

 resemble

0.67

 mirror

0.64

 embodies

0.64

it

0.63

 this

0.61

Activations Density 0.088%

phrases related to comparison or different aspects of something

expressions of multiple interpretations or perspectives on a topic

No Comments

No Known Activations