INDEX

Explanations

text related to system updates, error messages, and user instructions

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aget

-0.54

transQ

-0.47

Personendaten

-0.47

Fácil

-0.47

なるほど

-0.45

不然

-0.44

nok

-0.44

мость

-0.43

şte

-0.43

allible

-0.43

POSITIVE LOGITS

 please

2.40

 Please

2.10

Please

2.02

please

2.00

 PLEASE

1.87

 bitte

1.72

pls

1.71

PLEASE

1.65

plz

1.61

请

1.46

Activations Density 0.205%

text related to system updates, error messages, and user instructions

No Comments

No Known Activations