INDEX

Explanations

expressions of philosophical concepts and their interpretations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VideoCapture

-0.49

timewa

-0.47

Produzione

-0.47

 segn

-0.47

 segreto

-0.45

 rahasia

-0.45

fromnode

-0.45

 namanya

-0.44

 createSlice

-0.44

 alé

-0.44

POSITIVE LOGITS

 understandable

1.25

 concise

1.23

 easy

1.22

 digestible

1.21

 readable

1.13

 comprehen

1.12

 simplified

1.11

easy

1.10

 accessible

1.09

 succinct

1.09

Activations Density 0.402%

expressions of philosophical concepts and their interpretations

No Comments

No Known Activations