INDEX

Explanations

phrases related to companies or corporations

oai_token-act-pair · gpt-3.5-turbo

mentions of companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lect

-0.69

UCT

-0.66

oubt

-0.65

odox

-0.63

alam

-0.63

 Lanka

-0.63

requisite

-0.63

 guiActiveUn

-0.62

ividual

-0.62

 ILCS

-0.62

POSITIVE LOGITS

wide

0.90

 executives

0.83

 headquartered

0.80

 motto

0.77

 founders

0.77

's

0.73

 mogul

0.73

mens

0.72

 logos

0.71

 owner

0.70

Activations Density 0.045%

phrases related to companies or corporations

mentions of companies

No Comments

No Known Activations