INDEX

Explanations

terms related to skills and capabilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itself

-1.23

its

-0.98

 Itself

-0.94

 яке

-0.90

 Оно

-0.87

itself

-0.85

它的

-0.84

Its

-0.81

Its

-0.79

its

-0.76

POSITIVE LOGITS

themselves

0.87

 themselves

0.87

 herself

0.86

 которые

0.77

Those

0.71

 lesquelles

0.70

those

0.69

 those

0.67

herself

0.67

 които

0.65

Activations Density 0.022%

terms related to skills and capabilities

No Comments

No Known Activations