INDEX

Explanations

terms related to bus operations or directives given to bus operators

oai_token-act-pair · gpt-3.5-turbo

mentions of operators involved in various functions or activities

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

ioxide

-0.71

loe

-0.70

zl

-0.66

ilan

-0.65

PO

-0.64

auld

-0.64

western

-0.64

urd

-0.63

encers

-0.63

imm

-0.62

POSITIVE LOGITS

 operator

0.87

 Operator

0.80

 licenses

0.78

operator

0.76

otomy

0.76

 operators

0.75

 licences

0.75

operated

0.72

querade

0.70

 license

0.69

Activations Density 0.017%

terms related to bus operations or directives given to bus operators

mentions of operators involved in various functions or activities

No Comments

No Known Activations