INDEX

Explanations

distances expressed in kilometers

oai_token-act-pair · gpt-3.5-turbo

references to distances measured in kilometers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

comes

-0.73

 Bubble

-0.70

 bearer

-0.69

 Semin

-0.65

 Wong

-0.65

FORE

-0.61

Pot

-0.61

 Gott

-0.61

Universal

-0.60

 Crunch

-0.59

POSITIVE LOGITS

km

1.13

km

0.99

 kilometers

0.93

 kilometres

0.88

ghan

0.79

arij

0.77

obic

0.77

iasm

0.77

ijk

0.75

conservancy

0.74

Activations Density 0.008%

distances expressed in kilometers

references to distances measured in kilometers

No Comments

No Known Activations