INDEX

Explanations

names of individuals and specific references to characters or people in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

rungsseite

-0.80

 ModelExpression

-0.80

Rüyada

-0.78

 pinulongan

-0.68

EMEN

-0.68

uarts

-0.68

abadi

-0.67

onicus

-0.67

 виправивши

-0.67

Général

-0.66

POSITIVE LOGITS

0.63

NOPQRST

0.60

This

0.55

you

0.54

<tr>

0.54

You

0.53

if

0.52

 This

0.50

my

0.48

The

0.47

Activations Density 0.201%

names of individuals and specific references to characters or people in context

No Comments

No Known Activations