INDEX

Explanations

names of train or bus stations

oai_token-act-pair · gpt-3.5-turbo

references to various stations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ£

-0.86

interstitial

-0.77

onies

-0.76

theless

-0.76

Downloadha

-0.76

umers

-0.71

 traff

-0.68

paces

-0.68

mission

-0.67

yright

-0.67

POSITIVE LOGITS

 Station

1.18

eers

0.90

Station

0.80

 Depot

0.78

 Eleven

0.78

eering

0.77

DB

0.77

 Square

0.75

 Authority

0.75

 Royale

0.75

Activations Density 0.011%

names of train or bus stations

references to various stations

No Comments

No Known Activations