INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

key terms and entities related to players, roles, and responsibilities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

å§«

-0.78

¥µ

-0.77

Ħ¢

-0.75

rote

-0.66

dimension

-0.65

ilyn

-0.65

zhou

-0.62

unci

-0.62

umn

-0.62

éĸ

-0.61

POSITIVE LOGITS

 alone

0.98

 fault

0.96

 Incarn

0.86

 versus

0.77

 itself

0.76

 themselves

0.67

 rather

0.66

 plus

0.65

 Fault

0.64

hest

0.64

Activations Density 0.582%

proper nouns or specific names

key terms and entities related to players, roles, and responsibilities in various contexts

No Comments

No Known Activations