INDEX

Explanations

words related to uncertainty or potential outcomes, especially in the context of personal experiences and choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hoeddwyd

-0.71

<bos>

-0.69

Portail

-0.59

in

-0.51

RTS

-0.50

toThrow

-0.49

があると

-0.48

 contar

-0.47

on

-0.47

POSITIVE LOGITS

 myſelf

0.98

 Majefty

0.86

cshtml

0.82

 iſt

0.81

 ſche

0.79

 itſelf

0.78

 Jefus

0.77

 juſt

0.77

LookAnd

0.75

 ſever

0.74

Activations Density 0.108%

words related to uncertainty or potential outcomes, especially in the context of personal experiences and choices

No Comments

No Known Activations