INDEX

Explanations

references to scholarly titles or designations

oai_token-act-pair · gpt-3.5-turbo

terms related to academic achievement and scholarship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

cakes

-0.78

 rigs

-0.78

stones

-0.74

bread

-0.69

fits

-0.68

reb

-0.67

nuts

-0.65

 installations

-0.65

 bonuses

-0.65

 tweaks

-0.64

POSITIVE LOGITS

 Scholar

1.05

 Medline

0.99

 Crossref

0.97

ibli

0.94

 citation

0.93

lished

0.92

ibrary

0.91

 Journals

0.89

 CrossRef

0.87

umbn

0.82

Activations Density 0.034%

references to scholarly titles or designations

terms related to academic achievement and scholarship

No Comments

No Known Activations