INDEX

Explanations

references to medical conditions and health-related factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FH

-0.79

IH

-0.73

GH

-0.72

FH

-0.71

BH

-0.70

IH

-0.70

setH

-0.70

BH

-0.69

GH

-0.68

POSITIVE LOGITS

 height

0.83

tagHelperRunner

0.82

 handle

0.81

 Handle

0.77

height

0.76

 Handling

0.75

handle

0.74

 handling

0.74

 historical

0.73

Handle

0.72

Activations Density 0.480%

references to medical conditions and health-related factors

No Comments

No Known Activations