INDEX

Explanations

references to different types of therapy

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

Cull

-0.82

 Audiodateien

-0.80

Cus

-0.80

 arşivlendi

-0.79

 Arhivirano

-0.78

<tr>

-0.77

 ["",

-0.76

 Iwan

-0.76

RUnlock

-0.75

rul

-0.74

POSITIVE LOGITS

 therapy

1.84

 Therapy

1.75

Therapy

1.59

 THERAPY

1.56

therapy

1.44

 therapist

1.44

 therapists

1.43

 therapies

1.41

 Therap

1.33

therapist

1.32

Activations Density 0.083%

references to different types of therapy

No Comments

No Known Activations