INDEX

Explanations

instances where some entity is being listed

oai_token-act-pair · gpt-3.5-turbo

references to lists and enumerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

imeter

-0.85

ibe

-0.81

uca

-0.79

matter

-0.78

aretz

-0.77

clair

-0.76

ĸļ

-0.74

ivo

-0.73

poke

-0.73

edin

-0.72

POSITIVE LOGITS

 grievances

1.10

 allowable

1.08

 accomplishments

1.08

 names

1.05

 possibilities

1.05

 acron

1.00

 nominees

1.00

 candidates

0.99

 contenders

0.99

 occupations

0.97

Activations Density 0.176%

instances where some entity is being listed

references to lists and enumerations

No Comments

No Known Activations