INDEX

Explanations

prepositions and adverbs indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "along."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

adem

-0.70

ns

-0.69

BILITIES

-0.67

TY

-0.67

meg

-0.66

Spot

-0.66

apolis

-0.65

oric

-0.64

zel

-0.63

uum

-0.61

POSITIVE LOGITS

side

0.90

wagon

0.76

 Route

0.74

 routes

0.72

 Interstate

0.70

 corridors

0.69

 wagon

0.68

 Aven

0.68

linked

0.66

 highways

0.65

Activations Density 0.021%

prepositions and adverbs indicating location or direction

occurrences of the word "along."

No Comments

No Known Activations