INDEX

Explanations

references to officers and their roles or actions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

元

-0.65

Past

-0.65

ι

-0.63

ب

-0.63

л

-0.61

The

-0.61

nje

-0.61

ి

-0.60

times

-0.59

POSITIVE LOGITS

aarrggbb

0.97

Παραπομπές

0.95

Personendaten

0.95

addGap

0.94

 ProtoMessage

0.92

########.

0.89

 OFFICERS

0.88

officers

0.88

InstrumentedTest

0.88

 typelib

0.87

Activations Density 0.265%

references to officers and their roles or actions in various contexts

No Comments

No Known Activations