INDEX

Explanations

mentions of magical elements or objects

oai_token-act-pair · gpt-3.5-turbo

references to magical elements and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

upon

-0.79

consumer

-0.78

VP

-0.78

lr

-0.76

Cho

-0.70

xual

-0.69

ORS

-0.69

Fas

-0.67

Agg

-0.66

alez

-0.65

POSITIVE LOGITS

 magical

0.96

 beasts

0.85

magic

0.83

 arte

0.82

 resil

0.79

 magic

0.78

 teleportation

0.77

 artifact

0.77

 maiden

0.76

 wizard

0.76

Activations Density 0.009%

mentions of magical elements or objects

references to magical elements and experiences

No Comments

No Known Activations