INDEX

Explanations

sentences that include personal affirmations or declarations of identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Bisch

-0.61

Gimme

-0.60

ч

-0.55

vincing

-0.55

 polaire

-0.52

 fluores

-0.52

 vernac

-0.51

ട

-0.51

umpulkan

-0.51

 zask

-0.51

POSITIVE LOGITS

aarrggbb

0.94

mektedir

0.92

 utafitiHapana

0.83

maktadır

0.80

ofold

0.76

mıştır

0.74

のですね

0.71

 goederen

0.70

íncia

0.69

AutoScaleMode

0.69

Activations Density 0.504%

sentences that include personal affirmations or declarations of identity

No Comments

No Known Activations