INDEX

Explanations

proper nouns, specifically the name "Holland."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Holland."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

culation

-0.87

ctic

-0.80

ramid

-0.77

ãĥ£

-0.76

ceed

-0.76

vae

-0.76

ccording

-0.74

itutes

-0.74

ormal

-0.73

notations

-0.73

POSITIVE LOGITS

 Holland

0.98

inson

0.91

shire

0.90

stadt

0.84

 Gardens

0.79

 Gaal

0.76

Cob

0.75

ijn

0.74

 Tunnel

0.73

 Wink

0.73

Activations Density 0.010%

proper nouns, specifically the name "Holland."

mentions of the name "Holland."

No Comments

No Known Activations