INDEX

Explanations

words related to being inspired, motivated, or enthusiastic

oai_token-act-pair · gpt-3.5-turbo

words related to inspiration and emotional struggle

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

forth

-0.76

 Split

-0.70

numbered

-0.67

 ç¥ŀ

-0.65

matched

-0.63

 Scotia

-0.60

riad

-0.59

 Blessed

-0.59

elf

-0.59

 Cosmos

-0.59

POSITIVE LOGITS

atory

1.25

acies

1.19

acist

1.12

acles

1.11

ational

1.06

acular

1.05

ators

1.05

atorial

1.02

ysc

1.01

imental

1.00

Activations Density 0.017%

words related to being inspired, motivated, or enthusiastic

words related to inspiration and emotional struggle

No Comments

No Known Activations