INDEX

Explanations

phrases related to forward-looking statements and directional movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

={`/

-0.93

ibrill

-0.86

 समीक्षाओं

-0.85

didSet

-0.83

JSONException

-0.81

 DbSet

-0.81

AnchorTagHelper

-0.79

 Titans

-0.78

MeasureSpec

-0.77

 AssemblyCompany

-0.76

POSITIVE LOGITS

 forward

2.52

 Forward

2.48

Forward

2.42

 FORWARD

2.37

forward

2.35

 forwards

2.26

FORWARD

2.08

 forwarding

1.86

fwd

1.65

fow

1.57

Activations Density 0.062%

phrases related to forward-looking statements and directional movements

No Comments

No Known Activations