INDEX

Explanations

positive adjectives describing someone's character or abilities

oai_token-act-pair · gpt-3.5-turbo

words expressing praise and criticism about people's abilities or qualities

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

Negative Logits

idav

-0.73

ulton

-0.68

ARB

-0.68

 extensive

-0.65

armac

-0.63

cific

-0.63

risome

-0.62

 feasibility

-0.61

 elaborate

-0.60

yrinth

-0.60

POSITIVE LOGITS

enough

1.05

 enough

0.88

 Enough

0.80

friends

0.76

 negotiator

0.76

 sleeper

0.75

 undermin

0.72

blooded

0.72

looking

0.71

eyes

0.71

Activations Density 0.287%

positive adjectives describing someone's character or abilities

words expressing praise and criticism about people's abilities or qualities

No Known Activations