INDEX

Explanations

time indicators related to events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

SharedDtor

-0.86

EndGlobalSection

-0.83

addCriterion

-0.79

MigrationBuilder

-0.78

DebuggerNonUser

-0.74

SourceChecksum

-0.71

memoized

-0.71

(!__

-0.67

DebuggerStep

-0.66

QMetaType

-0.65

POSITIVE LOGITS

 pleaſure

0.59

extAlignment

0.59

 تضيفلها

0.57

 ſch

0.54

UVWXYZ

0.53

 تانيه

0.52

umptive

0.52

 ſmall

0.50

ſp

0.50

 iſt

0.49

Activations Density 0.352%

time indicators related to events or actions

No Comments

No Known Activations