INDEX

Explanations

locations or places described in relation to a specific event or action

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proximity or location

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

ilus

-0.85

Upload

-0.77

azeera

-0.77

Percent

-0.75

uese

-0.74

glers

-0.74

Files

-0.73

UX

-0.73

BILL

-0.73

artz

-0.72

POSITIVE LOGITS

 vicinity

0.82

sighted

0.80

 Vancouver

0.77

shore

0.77

 Bethlehem

0.75

 misses

0.74

Ń·

0.73

 near

0.72

 Fresno

0.72

 proximity

0.72

Activations Density 0.025%

locations or places described in relation to a specific event or action

phrases indicating proximity or location

No Comments

No Known Activations