INDEX

Explanations

titles and names of media works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 فريبيس

-0.96

 utafitiHapana

-0.74

tvguidetime

-0.73

Попис

-0.73

󠁴

-0.71

LEncoder

-0.68

adpleegd

-0.68

 tantôt

-0.68

 GenerationType

-0.66

 puissiez

-0.66

POSITIVE LOGITS

<eos>

0.93

↵↵

0.83

is

0.76

SequentialGroup

0.64

↵

0.63

↵↵↵

0.58

has

0.57

0.54

Activations Density 2.172%

titles and names of media works

No Comments

No Known Activations