INDEX

Explanations

specific terms related to the concept of trade-offs

oai_token-act-pair · gpt-3.5-turbo

references to payoffs and trade-offs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Rated

-0.64

ITED

-0.62

ATED

-0.61

Id

-0.61

Commun

-0.60

FUL

-0.59

 duct

-0.59

 Amend

-0.58

 IMAGES

-0.58

 repressive

-0.57

POSITIVE LOGITS

pring

1.31

offs

0.97

kies

0.85

lash

0.84

fits

0.84

terness

0.83

hots

0.81

peak

0.78

ourcing

0.77

folios

0.76

Activations Density 0.007%

specific terms related to the concept of trade-offs

references to payoffs and trade-offs

No Comments

No Known Activations