INDEX

Explanations

terms related to therapy and therapeutic practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ligente

-0.65

 Grun

-0.64

Sass

-0.64

 Wille

-0.62

<tr>

-0.62

 ["",

-0.62

<!--[

-0.61

Dob

-0.61

Klu

-0.61

nett

-0.61

POSITIVE LOGITS

 therapy

2.90

 Therapy

2.77

Therapy

2.53

therapy

2.44

 THERAPY

2.42

 therapies

2.18

 Therapies

2.02

 Therap

1.95

 therapists

1.95

 therapist

1.93

Activations Density 0.095%

terms related to therapy and therapeutic practices

No Comments

No Known Activations