INDEX

Explanations

technical terms related to specific products or technologies

oai_token-act-pair · gpt-3.5-turbo

brands or product names in a descriptive context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prest

-0.65

terday

-0.64

é¾įå¥ĳå£«

-0.62

=]

-0.60

etheless

-0.60

perty

-0.60

 compe

-0.58

viously

-0.58

 trave

-0.58

 undermin

-0.57

POSITIVE LOGITS

 Collection

0.83

 Handbook

0.83

 Museum

0.79

 Registry

0.79

 Awards

0.78

 Manifest

0.77

 Collective

0.77

 Project

0.76

 Catalog

0.76

 Series

0.76

Activations Density 0.723%

technical terms related to specific products or technologies

brands or product names in a descriptive context

No Comments

No Known Activations