INDEX

Explanations

terms related to clarification or stating information clearly

oai_token-act-pair · gpt-3.5-turbo

terminology related to explanation and clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

MET

-0.77

ï¸

-0.70

ren

-0.69

psc

-0.69

gins

-0.63

 Upton

-0.63

NetMessage

-0.62

lif

-0.61

aden

-0.60

advertising

-0.60

POSITIVE LOGITS

 clar

1.12

 clarified

0.92

 clarify

0.88

 wording

0.87

 clarification

0.86

ifications

0.83

ifying

0.79

initions

0.77

ifies

0.77

 deline

0.74

Activations Density 0.044%

terms related to clarification or stating information clearly

terminology related to explanation and clarification

No Comments

No Known Activations