INDEX

Explanations

numeric indicators or dates within sentences

oai_token-act-pair · gpt-3.5-turbo

locations and geographical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

wx

-0.68

 PLAN

-0.68

CLOSE

-0.64

 NAME

-0.62

GY

-0.60

ichever

-0.60

ailable

-0.59

LLOW

-0.59

PDATED

-0.58

Explore

-0.58

POSITIVE LOGITS

 last

0.86

 yesterday

0.81

 circa

0.81

 earlier

0.81

 beforehand

0.79

 shortly

0.76

ago

0.74

 prior

0.73

igslist

0.72

cember

0.70

Activations Density 0.677%

numeric indicators or dates within sentences

locations and geographical references

No Comments

No Known Activations