INDEX

Explanations

concepts related to changes in perception and memory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ⓧ

-0.64

skjaer

-0.59



-0.55

 numerus

-0.52

 lieb

-0.51

golf

-0.51

+#+#

-0.50

 secas

-0.50

rostis

-0.49

 руб

-0.48

POSITIVE LOGITS

 sights

0.85

 surroundings

0.85

 environment

0.75

 sensory

0.74

 environments

0.72

 smells

0.71

sensory

0.68

 stimuli

0.67

 immers

0.65

NameInMap

0.64

Activations Density 0.215%

concepts related to changes in perception and memory

No Comments

No Known Activations

concepts related to changes in perception and memory

No Comments

No Known Activations