INDEX

Explanations

references to specific entities or events from various fields such as politics, sports, and technology

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant organizations or entities

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

ZI

-0.57

tnc

-0.52

umbn

-0.48

NRL

-0.48

ocamp

-0.46

opian

-0.45

piring

-0.44

 Guant

-0.44

Wyr

-0.44

POSITIVE LOGITS

 meanwhile

0.84

 cannot

0.80

 consisted

0.80

 consists

0.79

 also

0.77

 tends

0.74

 replaced

0.73

 retains

0.73

 succeeded

0.72

 reverted

0.72

Activations Density 0.760%

references to specific entities or events from various fields such as politics, sports, and technology

proper nouns and significant organizations or entities

No Comments

No Known Activations