INDEX

Explanations

terms related to technical specifications and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Portale

-0.57

ROGEN

-0.49

imea

-0.47

httphttps

-0.47

ValueStyle

-0.46

יע

-0.46

PhysRev

-0.44

uttgart

-0.44

zaak

-0.44

ecma

-0.44

POSITIVE LOGITS

ſelf

0.79

EDEFAULT

0.76

 itſelf

0.74

 myſelf

0.72

 ſche

0.71

Efq

0.70

 traditionnels

0.67

 bisherigen

0.67

previously

0.66

 précédemment

0.65

Activations Density 0.742%

terms related to technical specifications and features

No Comments

No Known Activations