INDEX

Explanations

future tense statements with "will", "should", or similar words and clauses beginning with "that" or "which".

oai_token-act-pair · gemini-2.0-flash

legal/report excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawDesc

-0.59

 ब्रेकडाउन

-0.58

cstdlib

-0.56

 EconPapers

-0.54

wyl

-0.54

 CreateTagHelper

-0.54

новременно

-0.54

usha

-0.54

 wire

-0.53

 tslint

-0.53

POSITIVE LOGITS

 recev

0.57

be

0.57

hdashline

0.54

courir

0.54

 SwitchCompat

0.53

afficheront

0.46

 assin

0.45

 være

0.45

 được

0.45

Comté

0.44

Activations Density 0.424%

future tense statements with "will", "should", or similar words and clauses beginning with "that" or "which".

legal/report excerpts

No Comments

No Known Activations