INDEX

Explanations

locations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "place."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

igans

-0.67

quel

-0.66

CHAT

-0.65

agascar

-0.65

rd

-0.64

irl

-0.62

umin

-0.61

olyn

-0.60

jin

-0.60

archives

-0.60

POSITIVE LOGITS

holder

1.14

holders

1.08

bos

1.05

ername

0.89

upon

0.79

knife

0.78

bo

0.78

ngth

0.73

 Temperature

0.69

down

0.69

Activations Density 0.032%

locations

variations of the word "place."

No Comments

No Known Activations