INDEX

Explanations

terms related to evaluation and measurement in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

BeginContext

-0.70

خاذ

-0.57

ThroughAttribute

-0.55

IsContent

-0.54

 Exactos

-0.54

[]:

-0.53

bestos

-0.52

 Gilmore

-0.52

endaft

-0.51

 <<<<<<<<<<<<<<

-0.51

POSITIVE LOGITS

 tank

0.93

 aquarium

0.82

Tank

0.81

HOB

0.80

tank

0.80

 Aquarium

0.75

 Tank

0.74

 tanks

0.72

 substrate

0.67

TANK

0.67

Activations Density 0.127%

terms related to evaluation and measurement in a scientific context

No Comments

No Known Activations