INDEX

Explanations

names related to the term "Rand"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Rand" and its variations

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

 scene

-0.72

 operative

-0.69

 bubbles

-0.66

 Cyprus

-0.63

 bubble

-0.61

 wreckage

-0.61

OG

-0.61

sky

-0.60

NFL

-0.60

TL

-0.60

POSITIVE LOGITS

rand

4.99

Rand

1.87

 rand

1.74

 RAND

1.20

rade

1.11

random

1.10

ande

1.05

 Rand

1.04

ourt

1.03

rill

1.03

Activations Density 0.018%

names related to the term "Rand"

occurrences of the name "Rand" and its variations

No Comments

No Known Activations