INDEX

Explanations

terms related to research and bias

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

preceding or related to "bias"

np_acts-logits-general · gemini-2.0-flash

bias and avoiding bias

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AddTagHelper

-0.57

 Inscrivez

-0.54

expandindo

-0.54

ChildScrollView

-0.53

ConstraintMaker

-0.52

 hidrá

-0.50

ereum

-0.50

 FetchType

-0.49

 réguli

-0.48

 PublicKey

-0.48

POSITIVE LOGITS

 bias

2.09

 biased

1.93

 biases

1.72

 Bias

1.65

bias

1.58

biased

1.57

Bias

1.49

biases

1.31

BIAS

1.29

 favou

1.12

Activations Density 0.701%

terms related to research and bias

preceding or related to "bias"

bias and avoiding bias

No Comments

No Known Activations