INDEX

Explanations

terms related to modification or alteration of data or code

oai_token-act-pair · gpt-3.5-turbo

terms related to modifying or changing software and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ublic

-0.78

GV

-0.76

gart

-0.74

glas

-0.73

iland

-0.72

âĹ¼

-0.71

ç«

-0.68

ritis

-0.66

gets

-0.65

dding

-0.64

POSITIVE LOGITS

 parameters

1.02

 existing

0.99

 settings

0.90

 variables

0.88

 thresholds

0.84

 portions

0.83

 behaviour

0.83

 aspects

0.83

 wording

0.82

 permissions

0.81

Activations Density 0.134%

terms related to modification or alteration of data or code

terms related to modifying or changing software and configurations

No Comments

No Known Activations