INDEX

Explanations

the beginning and end markers of textual segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

principalTable

-0.74

 itſelf

-0.70

 pinulongan

-0.69

 jsPsych

-0.68

 esternos

-0.65

yaszt

-0.64

jsonwebtoken

-0.64

 enfans

-0.64

 deoarece

-0.64

 betweenstory

-0.63

POSITIVE LOGITS

no

0.66

 كومونز

0.65

omin

0.63

0.61

 cool

0.60

пло

0.59

 Cool

0.59

Vis

0.58

 Nice

0.58

fer

0.57

Activations Density 0.185%

the beginning and end markers of textual segments

No Comments

No Known Activations