INDEX

Explanations

mention of past events or recall of information

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

Followed by "that"

np_acts-logits-general · gemini-2.0-flash

observation and claims

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Efq

-0.96

 Majefty

-0.94

 esternos

-0.92

 المعيارى

-0.89

IntoConstraints

-0.88

 فريبيس

-0.88

 Shakspeare

-0.86

RenderAtEndOf

-0.86

 Monfieur

-0.86

 CreateTagHelper

-0.83

POSITIVE LOGITS

 however

0.69

 inoltre

0.66

 these

0.62

However

0.61

 also

0.58

 therefore

0.56

 this

0.54

 However

0.54

 azonban

0.49

 cependant

0.48

Activations Density 0.461%

mention of past events or recall of information

Followed by "that"

observation and claims

No Comments

No Known Activations