INDEX

Explanations

references to villagers and their activities or characteristics

oai_token-act-pair · gpt-3.5-turbo

mentions of villagers in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Dragonbound

-0.72

olic

-0.69

umbn

-0.69

anian

-0.69

ept

-0.68

hub

-0.68

Topics

-0.67

Techn

-0.67

————————

-0.67

ï¸

-0.66

POSITIVE LOGITS

 villagers

1.09

 vill

0.94

iage

0.83

ager

0.79

 villages

0.78

ongs

0.77

folk

0.76

 Grave

0.76

agers

0.75

iae

0.75

Activations Density 0.012%

references to villagers and their activities or characteristics

mentions of villagers in varying contexts

No Comments

No Known Activations