INDEX

Explanations

adjectives or past participles indicating likelihood or capacity

oai_token-act-pair · gpt-3.5-turbo

words indicating feasibility or likelihood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ortment

-0.82

cipl

-0.71

viron

-0.69

mosp

-0.69

guyen

-0.63

ells

-0.63

arlane

-0.61

lab

-0.60

sheets

-0.60

uclear

-0.59

POSITIVE LOGITS

 unless

0.79

 srfAttach

0.77

 anyway

0.76

.ãĢį

0.74

 anymore

0.74

 without

0.73

 regardless

0.72

 irrespective

0.72

.–

0.70

 Jagu

0.70

Activations Density 0.200%

adjectives or past participles indicating likelihood or capacity

words indicating feasibility or likelihood

No Comments

No Known Activations