INDEX

Explanations

repeated instances of the token/signifier "ss"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Larkin

-0.79

!*\

-0.77

Zin

-0.71

Jau

-0.71

]-->

-0.70

 McLaughlin

-0.69

ADVERTISEMENT

-0.69

ERMIN

-0.69

`/

-0.68

Vino

-0.68

POSITIVE LOGITS

SS

1.62

ss

1.58

ss

1.52

SS

1.48

ess

1.48

Ss

1.16

ESS

1.15

SSS

1.07

MESS

1.04

 MESS

0.97

Activations Density 0.092%

repeated instances of the token/signifier "ss"

No Comments

No Known Activations