INDEX

Explanations

instances of the prefix "pr" suggesting references to psychological or emotional themes

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.52

Autoritní

-0.63

ⓧ

-0.60

 springfox

-0.60

 ratify

-0.58

 dovrebbero

-0.57

 ovunque

-0.55

 kaynağından

-0.54

PerformLayout

-0.54

HideFlags

-0.54

POSITIVE LOGITS

Pr

1.28

pr

1.27

Pr

1.17

pr

1.12

PR

1.05

 Prat

1.01

PR

0.97

Pru

0.95

Prat

0.93

Pra

0.89

Activations Density 0.103%

instances of the prefix "pr" suggesting references to psychological or emotional themes

No Comments

No Known Activations