INDEX

Explanations

personal pronouns and verbs indicating personal actions or interactions

oai_token-act-pair · gpt-3.5-turbo

terms related to various digital media formats and 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

 favor

-0.90

 accrued

-0.82

 eleph

-0.80

lim

-0.78

 conflicted

-0.78

 charter

-0.78

 cher

-0.77

 scaling

-0.77

ow

-0.76

 consolidation

-0.76

POSITIVE LOGITS

1.37

1.36

1.34

Mal

1.32

1.30

Bl

1.29

World

1.29

Activations Density 0.344%

personal pronouns and verbs indicating personal actions or interactions

terms related to various digital media formats and contexts

No Comments

No Known Activations