INDEX

Explanations

specific references to customer service issues and complaints related to products

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

Follows "after," indefinite pronouns, or unclosed brackets

np_acts-logits-general · gemini-2.0-flash

past events and sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 often

-0.63

often

-0.59

}))

-0.58

 souvent

-0.56

Often

-0.56

 Often

-0.55

 nowadays

-0.54

InitVars

-0.53

 sometimes

-0.52

 manchmal

-0.52

POSITIVE LOGITS

 supuestamente

0.81

 ANOTHER

0.74

 AGAIN

0.70

 apologized

0.70

 requested

0.69

 supposedly

0.67

 emailed

0.67

 rağmen

0.66

 supposed

0.65

 promised

0.65

Activations Density 0.223%

specific references to customer service issues and complaints related to products

Follows "after," indefinite pronouns, or unclosed brackets

past events and sequences

No Comments

No Known Activations