INDEX

Explanations

mentions of same-sex relationships and related legal matters

oai_token-act-pair · gpt-3.5-turbo

discussions about same-sex marriage

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

 Canaver

-0.72

stanbul

-0.71

 nerv

-0.70

 Sawyer

-0.69

 Cannon

-0.67

 Hyder

-0.66

 Cotton

-0.65

 Guru

-0.65

 Gunn

-0.64

 Mermaid

-0.64

POSITIVE LOGITS

sized

1.12

level

1.05

origin

1.01

bodied

1.01

named

1.01

sided

0.99

minded

0.98

income

0.97

interest

0.97

themed

0.96

Activations Density 0.040%

mentions of same-sex relationships and related legal matters

discussions about same-sex marriage

No Comments

No Known Activations