INDEX

Explanations

references to subjective interpretations of historical facts and events

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

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

TagHelper

-0.64

DoubleQuotes

-0.63

ленность

-0.59

исленность

-0.59

MessageOf

-0.57

сылкі

-0.57

BeginContext

-0.55

CodedInputStream

-0.55

OfType

-0.54

 AssemblyProduct

-0.54

POSITIVE LOGITS

 imaginary

1.60

 fictional

1.49

 imagination

1.48

 fictitious

1.36

imaginary

1.36

 invented

1.31

 imagined

1.31

imagination

1.30

 fiction

1.29

Imaginary

1.25

Activations Density 0.458%

references to subjective interpretations of historical facts and events

No Comments

No Known Activations