INDEX

Explanations

keywords related to participation in events or activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "participating" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

forward

-0.91

tight

-0.77

pel

-0.73

nu

-0.72

cut

-0.70

bul

-0.69

flu

-0.68

clear

-0.67

celona

-0.66

thur

-0.66

POSITIVE LOGITS

 participating

1.02

 participates

0.97

 Particip

0.91

 participate

0.87

ivity

0.83

 Participation

0.82

 participated

0.81

 participation

0.81

natureconservancy

0.78

 participant

0.76

Activations Density 0.006%

keywords related to participation in events or activities

instances of the word "participating" in various contexts

No Comments

No Known Activations