INDEX

Explanations

terms related to effects or results, particularly in a scientific or analytical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

httphttps

-0.76

 ProtoMessage

-0.69

 Audiodateien

-0.69

BeginContext

-0.65

govine

-0.65

 виправивши

-0.65

цездатний

-0.65

 ChromeDriver

-0.64

--]

-0.63

EDEFAULT

-0.62

POSITIVE LOGITS

Impacts

0.97

 impacts

0.92

 Impacts

0.88

 impact

0.83

 Impact

0.80

 IMPACT

0.74

 effect

0.74

 impacting

0.71

 affect

0.70

impact

0.70

Activations Density 0.135%

terms related to effects or results, particularly in a scientific or analytical context

No Comments

No Known Activations