INDEX

Explanations

keywords related to software and tech companies

oai_token-act-pair · gpt-3.5-turbo

specific names of software, companies, and people mentioned 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 @ 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

xon

-0.71

ammy

-0.70

orsche

-0.69

nz

-0.68

ciation

-0.68

ãĥ£

-0.64

mble

-0.64

rero

-0.64

uminati

-0.63

onies

-0.63

POSITIVE LOGITS

's

0.78

 itself

0.73

 himself

0.69

Care

0.68

 herself

0.66

 Citadel

0.66

 Himself

0.65

HQ

0.58

 brass

0.58

 merchandise

0.57

Activations Density 0.427%

keywords related to software and tech companies

specific names of software, companies, and people mentioned in various contexts

No Comments

No Known Activations