INDEX

Explanations

corporate entities and trade-related terms

oai_token-act-pair · gpt-3.5-turbo

names of companies and organizations

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

 trope

-0.87

 recess

-0.81

 poem

-0.81

 pardon

-0.81

 literal

-0.80

 portrait

-0.79

vag

-0.77

rhy

-0.76

 rage

-0.75

 narrated

-0.75

POSITIVE LOGITS

Shares

1.41

 Holdings

1.32

Company

1.17

Companies

1.15

 Labs

1.09

Pay

1.08

Soft

1.08

 Technologies

1.07

 Ventures

1.05

 Pharmaceutical

1.05

Activations Density 0.399%

corporate entities and trade-related terms

names of companies and organizations

No Comments

No Known Activations