INDEX

Explanations

numbers denoting specific subsections or points within a document

oai_token-act-pair · gpt-3.5-turbo

sequences of numbers referencing articles, studies, or technical specifications

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

oyd

-0.88

atem

-0.84

ãĤ¡

-0.74

ogue

-0.69

ation

-0.67

igating

-0.66

nih

-0.66

omial

-0.66

rid

-0.64

 Beckham

-0.64

POSITIVE LOGITS

0.93

0.91

teenth

0.91

0.90

th

0.88

0.87

0.86

0.85

Activations Density 0.033%

numbers denoting specific subsections or points within a document

sequences of numbers referencing articles, studies, or technical specifications

No Comments

No Known Activations