INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

references to past events or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 therein

-0.85

pite

-0.76

aby

-0.73

 Matters

-0.72

pet

-0.72

ogie

-0.69

oples

-0.69

nyder

-0.68

results

-0.67

 secondly

-0.67

POSITIVE LOGITS

 precedent

0.72

 existed

0.68

 Henri

0.65

esley

0.64

 Cass

0.63

 Computing

0.63

 Atari

0.61

 segregated

0.60

 assumed

0.60

 Binary

0.60

Activations Density 0.392%

dates or time periods

references to past events or historical contexts

No Comments

No Known Activations