INDEX

Explanations

terms related to the concept of "spot" or "tan."

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

ⓧ

-0.66

 Expressway

-0.60

CloseOperation

-0.60

unbind

-0.60

StackNavigator

-0.59

 žaid

-0.59

 Ausnahme

-0.58

󠁴

-0.57

 ProtoMessage

-0.57

CodedInputStream

-0.56

POSITIVE LOGITS

 Spot

0.77

 SPOT

0.74

 spot

0.72

spot

0.70

tan

0.69

Spot

0.66

Tan

0.63

tan

0.61

ContentAlignment

0.60

Tan

0.58

Activations Density 0.147%

terms related to the concept of "spot" or "tan."

No Comments

No Known Activations