INDEX

Explanations

references to "force" in various contexts

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

 fær

-0.84

thmetic

-0.82

 larmes

-0.81

ſelf

-0.81

 Ratt

-0.80

katapos

-0.78

 Wann

-0.77

thral

-0.76

^(@)

-0.76

thentication

-0.76

POSITIVE LOGITS

 force

2.24

 Force

2.13

force

2.11

Force

2.01

 FORCE

2.00

 forces

1.96

 Forces

1.88

FORCE

1.86

forces

1.82

Forces

1.72

Activations Density 0.046%

references to "force" in various contexts

No Comments

No Known Activations