INDEX

Explanations

references to small entities or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WithIdentifier

-0.58

PYX

-0.55

 scolas

-0.48

ільки

-0.48

RepeatedField

-0.48

 utama

-0.47

CodeAttribute

-0.46

DebuggerNonUser

-0.46

Neden

-0.45

sidemargin

-0.45

POSITIVE LOGITS

Small

1.13

 Small

1.12

 SMALL

1.06

small

1.04

SMALL

1.01

 small

0.98

scale

0.90

pox

0.88

 scale

0.86

Kleine

0.81

Activations Density 0.137%

references to small entities or concepts

No Comments

No Known Activations