INDEX

Explanations

words related to finding inspiration or being inspired

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "inspiration" and related concepts of creativity and motivation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ington

-0.77

 Strait

-0.68

erm

-0.67

restling

-0.65

talk

-0.64

tein

-0.64

 hump

-0.64

ells

-0.63

ophon

-0.62

 Canad

-0.61

POSITIVE LOGITS

 inspiration

1.13

iration

1.06

 muse

0.91

 inspir

0.85

 inspiring

0.82

 inspired

0.79

apache

0.78

 Cosponsors

0.75

DragonMagazine

0.74

 Insp

0.72

Activations Density 0.025%

words related to finding inspiration or being inspired

occurrences of the word "inspiration" and related concepts of creativity and motivation

No Comments

No Known Activations