INDEX

Explanations

mentions of panels or panelists in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of "panel" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lihood

-0.67

 Madison

-0.67

ensor

-0.63

CN

-0.62

 fundament

-0.62

tics

-0.61

 CARD

-0.60

 Laur

-0.60

gins

-0.59

 Dame

-0.59

POSITIVE LOGITS

ists

1.30

igans

1.12

ist

1.10

igan

0.91

isted

0.86

naire

0.82

ahon

0.81

isting

0.81

iser

0.80

isode

0.79

Activations Density 0.035%

mentions of panels or panelists in various contexts

mentions of "panel" and its variations in context

No Comments

No Known Activations