INDEX

Explanations

names of people involved in historical or educative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

InputBorder

-0.64

ftagPool

-0.63

willReturn

-0.59

ISupport

-0.58

writeField

-0.56

<![

-0.55

PhysRevD

-0.54

 BorderRadius

-0.54

migrationBuilder

-0.52

unts

-0.51

POSITIVE LOGITS

 envisioned

0.68

 spiega

0.66

 first

0.66

 explains

0.66

 wanted

0.65

 noticed

0.64

 realized

0.63

 souhait

0.62

 needed

0.62

 reasoned

0.61

Activations Density 0.399%

names of people involved in historical or educative contexts

No Comments

No Known Activations