INDEX

Explanations

terms related to place names or businesses

oai_token-act-pair · gpt-3.5-turbo

specific names or titles associated with various subjects or references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 conclud

-0.70

anwhile

-0.70

 conducive

-0.66

theless

-0.66

etheless

-0.65

åĳ

-0.64

 referen

-0.63

 credible

-0.60

 describ

-0.59

 concerned

-0.59

POSITIVE LOGITS

romancer

0.78

itars

0.78

tones

0.77

zer

0.72

otto

0.71

oot

0.69

iman

0.69

rot

0.68

oms

0.68

pit

0.67

Activations Density 0.538%

terms related to place names or businesses

specific names or titles associated with various subjects or references in the text

No Comments

No Known Activations