INDEX

Explanations

professionals in the sports field

oai_token-act-pair · gpt-3.5-turbo

names of people or characters

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

 Rowling

-0.77

 Dorothy

-0.72

 Cheryl

-0.71

 Fiona

-0.69

 Judith

-0.69

SPONSORED

-0.69

 Eleanor

-0.69

 UNCLASSIFIED

-0.68

ricia

-0.68

 Louise

-0.67

POSITIVE LOGITS

 Rookie

0.80

 coached

0.76

 injury

0.76

 teammate

0.73

 defensive

0.72

 preseason

0.71

 depth

0.70

iggs

0.69

 rookie

0.69

 fullback

0.68

Activations Density 0.182%

professionals in the sports field

names of people or characters

No Comments

No Known Activations