INDEX

Explanations

various symbols/punctuation and code snippets, as well as words related to licensing and software

oai_token-act-pair · gemini-2.0-flash

demonstrative pronouns

np_token-act-pair-logits · gpt-4o-mini

this and these

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BSITE

-0.58

ękuję

-0.47

Hauptartikel

-0.47

 AudioClip

-0.47

XtraGrid

-0.45

razione

-0.45

äki

-0.45

ngdoc

-0.45

 nonUne

-0.45

istique

-0.45

POSITIVE LOGITS

 these

3.06

 this

3.00

these

2.56

this

2.33

 THESE

2.08

 These

2.06

These

2.06

 queste

1.95

 этих

1.90

 này

1.87

Activations Density 11.137%

various symbols/punctuation and code snippets, as well as words related to licensing and software

demonstrative pronouns

this and these

No Comments

No Known Activations