INDEX

Explanations

actions related to returning or restoring to a previous state or condition

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

 OFDb

-0.81

ftagPool

-0.80

PerformLayout

-0.77

 Vikipedi

-0.74

CONSIN

-0.72

nologue

-0.72

URLException

-0.72

 kasarigan

-0.71

twimg

-0.71

ècie

-0.70

POSITIVE LOGITS

 lost

0.64

 original

0.61

lost

0.59

Lost

0.57

 normality

0.56

 Lost

0.56

回到了

0.54

 normalcy

0.54

 LOST

0.53

Original

0.52

Activations Density 0.237%

actions related to returning or restoring to a previous state or condition

No Comments

No Known Activations