INDEX

Explanations

names of individuals related to team competitions in sports

oai_token-act-pair · gpt-3.5-turbo

parentheses and their usage in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 overwhelming

-0.81

 deval

-0.75

 normalized

-0.72

 conver

-0.68

 incon

-0.66

 shaming

-0.65

 consumers

-0.65

 polarized

-0.65

 alike

-0.64

 limitless

-0.63

POSITIVE LOGITS

Assistant

0.97

Jr

0.97

PhD

0.94

hower

0.84

croft

0.83

cair

0.83

who

0.81

QC

0.81

cox

0.80

Fra

0.79

Activations Density 0.153%

names of individuals related to team competitions in sports

parentheses and their usage in text

No Comments

No Known Activations