INDEX

Explanations

mentions or discussions related to beta testing and testers

oai_token-act-pair · gpt-3.5-turbo

mentions of "beta" associated with testing or versions of software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

advertisement

-0.89

ĸļ

-0.85

metics

-0.80

say

-0.79

erva

-0.76

AMI

-0.75

aws

-0.75

erved

-0.74

encer

-0.73

erick

-0.73

POSITIVE LOGITS

 beta

1.04

beta

0.96

 Beta

0.91

Beta

0.87

 blocker

0.87

 testers

0.87

 blockers

0.84

 Centauri

0.83

 alpha

0.80

alpha

0.75

Activations Density 0.010%

mentions or discussions related to beta testing and testers

mentions of "beta" associated with testing or versions of software

No Comments

No Known Activations