INDEX

Explanations

questions being asked by interviewers

oai_token-act-pair · gpt-3.5-turbo

instances of the word "asked" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Fit

-0.86

jam

-0.66

MpServer

-0.64

Magn

-0.61

equal

-0.61

agement

-0.61

Js

-0.59

execute

-0.59

ECD

-0.58

Minecraft

-0.58

POSITIVE LOGITS

 rhet

1.09

 questions

1.02

 quizz

0.95

 Questions

0.90

 asked

0.88

 sarcast

0.84

 specifically

0.83

ioned

0.83

 probing

0.83

 posed

0.80

Activations Density 0.024%

questions being asked by interviewers

instances of the word "asked" in various contexts

No Comments

No Known Activations