INDEX

Explanations

instances of words related to describing or mentioning something in detail

oai_token-act-pair · gpt-3.5-turbo

instances of words related to documentation and references

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

ingham

-0.69

PU

-0.68

isol

-0.65

ateurs

-0.64

uala

-0.63

âĢ¢âĢ¢âĢ¢âĢ¢

-0.62

 Clicker

-0.62

riot

-0.61

ateur

-0.61

cot

-0.60

POSITIVE LOGITS

 herein

0.98

 hereafter

0.90

 above

0.87

 supra

0.84

 Parenthood

0.82

 below

0.81

by

0.79

 inconsist

0.79

 therein

0.78

 separately

0.77

Activations Density 0.187%

instances of words related to describing or mentioning something in detail

instances of words related to documentation and references

No Comments

No Known Activations