INDEX

Explanations

company names and financial terms

oai_token-act-pair · gpt-3.5-turbo

mentions of companies and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 recess

-0.89

 extraord

-0.76

 poem

-0.74

 impe

-0.72

 rage

-0.70

rhy

-0.70

 filibuster

-0.70

 trope

-0.68

 fallacy

-0.68

 disorder

-0.68

POSITIVE LOGITS

 Holdings

1.15

 subsidiaries

1.10

Company

1.10

Shares

1.09

Companies

0.99

 Industries

0.99

 Corp

0.98

 Labs

0.98

 Corporation

0.97

 Laboratories

0.96

Activations Density 0.312%

company names and financial terms

mentions of companies and brands

No Comments

No Known Activations