INDEX

Explanations

terms related to military or strategic maneuvers

oai_token-act-pair · gpt-3.5-turbo

instances of the word "tro" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ayne

-0.82

 Seal

-0.80

 Sussex

-0.76

Pul

-0.72

escal

-0.72

edar

-0.71

Pug

-0.70

fighters

-0.70

ultan

-0.70

 Nano

-0.68

POSITIVE LOGITS

tro

2.65

Fra

1.52

Vog

1.25

 Frankfurt

1.16

ruck

1.05

Erd

1.05

 repro

1.00

 ripe

0.99

 Fors

0.95

 MÃ¼

0.94

Activations Density 0.048%

terms related to military or strategic maneuvers

instances of the word "tro" in various contexts

No Comments

No Known Activations