INDEX

Explanations

references to the word "Av" followed by a number, potentially related to different contexts or individuals named "Av."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Av" or variations of it in different contexts

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

utenant

-0.76

hyde

-0.73

FORMATION

-0.69

 Candy

-0.65

zsche

-0.64

bered

-0.63

ngth

-0.63

 inaccessible

-0.62

ãģ¦

-0.62

cipline

-0.61

POSITIVE LOGITS

atars

1.19

ocado

1.05

ril

1.01

raham

1.01

atar

1.00

iator

1.00

iol

0.97

iva

0.96

iations

0.95

ith

0.95

Activations Density 0.007%

references to the word "Av" followed by a number, potentially related to different contexts or individuals named "Av."

occurrences of the name "Av" or variations of it in different contexts

No Comments

No Known Activations