INDEX

Explanations

locations or place names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of places or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 carbohyd

-0.92

 retard

-0.66

 Canaver

-0.66

ULAR

-0.65

 theorist

-0.63

 odds

-0.61

orsche

-0.61

Lear

-0.61

 conductor

-0.61

 mechanically

-0.60

POSITIVE LOGITS

 Junction

1.20

 Village

1.09

 Valley

1.08

 Township

1.08

 Gardens

1.07

 Island

1.06

 Peninsula

1.04

 Town

1.01

 Cove

1.00

 Borough

1.00

Activations Density 0.308%

locations or place names

proper nouns, particularly names of places or locations

No Comments

No Known Activations