INDEX

Explanations

specific years

oai_token-act-pair · gpt-3.5-turbo

references to specific historical years

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ularity

-0.69

venge

-0.67

ioned

-0.66

ndra

-0.65

opher

-0.64

aith

-0.64

parency

-0.63

imon

-0.63

resso

-0.62

amin

-0.62

POSITIVE LOGITS

å¹

0.77

0.76

0.74

-'

0.70

 onwards

0.69

0.68

çļ

0.68

keley

0.68

Activations Density 0.049%

specific years

references to specific historical years

No Comments

No Known Activations