INDEX

Explanations

terms related to psychological and emotional trauma, particularly focusing on attachment issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

usehen

-0.64

-0.60

 inspiración

-0.58

новништво

-0.56

 snee

-0.56

 intermission

-0.55

 viſ

-0.55

 sneeze

-0.55

 stewards

-0.54

 Roskov

-0.54

POSITIVE LOGITS

 self

0.88

ego

0.74

 Self

0.73

Freud

0.72

 psycho

0.71

 Freud

0.71

 unresolved

0.70

 projection

0.69

Ego

0.68

 repressed

0.67

Activations Density 0.302%

terms related to psychological and emotional trauma, particularly focusing on attachment issues

No Comments

No Known Activations