INDEX

Explanations

numerical patterns or codes embedded within text

oai_token-act-pair · gpt-3.5-turbo

numeric values or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

anooga

-0.76

 millenn

-0.70

 explanatory

-0.67

inery

-0.67

ifice

-0.67

 prem

-0.66

 stressing

-0.65

 makeshift

-0.64

hon

-0.64

 tremend

-0.63

POSITIVE LOGITS

.............

0.99

GMT

0.93

GMT

0.88

CTR

0.84

bps

0.82

çĶ°

0.80

0.79

0.78

Activations Density 0.070%

numerical patterns or codes embedded within text

numeric values or identifiers

No Comments

No Known Activations