INDEX

Explanations

words related to filtering and categorization

oai_token-act-pair · gpt-3.5-turbo

references to filtering and filtration processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

FUL

-0.78

 Signal

-0.76

 Bread

-0.74

ONES

-0.70

 Button

-0.67

CV

-0.67

Ins

-0.67

 Booth

-0.66

 Sands

-0.66

 Ready

-0.65

POSITIVE LOGITS

fil

1.06

 juven

1.00

lete

0.89

 manif

0.87

itage

0.86

itional

0.85

ysis

0.82

 corrid

0.82

ulators

0.81

itionally

0.80

Activations Density 0.011%

words related to filtering and categorization

references to filtering and filtration processes

No Comments

No Known Activations