INDEX

Explanations

mentions of the word "rap" at varying strengths of activation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rap" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wills

-0.75

 Takeru

-0.67

bright

-0.63

 Mississ

-0.62

 recall

-0.62

 Jong

-0.59

 Schwarz

-0.59

 Lauder

-0.58

 Garg

-0.58

natureconservancy

-0.58

POSITIVE LOGITS

odcast

1.15

rap

1.09

hene

0.96

olitics

0.94

heny

0.94

artisan

0.89

ixel

0.88

inion

0.87

ascal

0.86

oline

0.85

Activations Density 0.007%

mentions of the word "rap" at varying strengths of activation

instances of the word "rap" in various contexts

No Comments

No Known Activations