INDEX

Explanations

expressions related to the significance and impact of personal and professional experiences

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

Auxiliary verbs followed by "not"

np_acts-logits-general · gemini-2.0-flash

be verbs followed by negation or state

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 oneself

-0.64

 fallu

-0.61

 ourselves

-0.60

 perfons

-0.58

 myſelf

-0.58

 indoss

-0.54

Portale

-0.54

ddots

-0.54

 themſelves

-0.54

 yourself

-0.53

POSITIVE LOGITS

 consist

0.65

tvguidetime

0.62

ActionCreators

0.60

 виправивши

0.59

 AssemblyCompany

0.59

gebob

0.58

moine

0.54

 revolve

0.53

 متعلقه

0.53

 Процитовано

0.53

Activations Density 0.333%

expressions related to the significance and impact of personal and professional experiences

Auxiliary verbs followed by "not"

be verbs followed by negation or state

No Comments

No Known Activations