INDEX

Explanations

terms related to evolution and its processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DockStyle

-0.86

SourceChecksum

-0.77

новниш

-0.75

AndEndTag

-0.71

StreetMap

-0.69

<()>

-0.69

inerary

-0.67

CodedInputStream

-0.65

UpInside

-0.65

borderSide

-0.64

POSITIVE LOGITS

 once

0.76

Once

0.70

 Regional

0.68

 Once

0.67

 evolution

0.63

once

0.61

 regional

0.58

 Evolution

0.58

Regional

0.56

 ONCE

0.55

Activations Density 0.182%

terms related to evolution and its processes

No Comments

No Known Activations