INDEX

Explanations

error messages and technical instructions

oai_token-act-pair · gpt-3.5-turbo

phrases related to warnings or errors in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

amins

-0.79

 respectively

-0.69

agogue

-0.61

kefeller

-0.60

 pilgr

-0.59

estyles

-0.59

anches

-0.57

nces

-0.56

aina

-0.55

styles

-0.54

POSITIVE LOGITS

 malice

0.69

 causation

0.61

 urgency

0.61

 vengeance

0.59

 negligence

0.58

"]=>

0.57

 delay

0.57

 inaction

0.56

onement

0.56

IPM

0.56

Activations Density 1.949%

error messages and technical instructions

phrases related to warnings or errors in a technical context

No Comments

No Known Activations