INDEX

Explanations

a series of words found in questions on stackoverflow or similar tech support sites.

oai_token-act-pair · gemini-2.0-flash

present tense and past tense verbs

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

Code errors and debugging

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

BASEPATH

-0.53

WebVitals

-0.47

ote

-0.44

numerusform

-0.42

rafas

-0.41

 fruiting

-0.41

خب

-0.41

 Yugoslav

-0.41

 κάν

-0.40

ModelMap

-0.40

POSITIVE LOGITS

is

1.10

was

0.91

isn

0.76

has

0.75

+#+

0.73

 فريبيس

0.73

 does

0.73

 gets

0.72

 will

0.70

 hasn

0.69

Activations Density 4.791%

a series of words found in questions on stackoverflow or similar tech support sites.

present tense and past tense verbs

Code errors and debugging

No Comments

No Known Activations