INDEX

Explanations

words related to months

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "une" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ories

-0.89

loo

-0.77

onial

-0.75

draw

-0.74

lishes

-0.71

matic

-0.70

rants

-0.70

oret

-0.70

ivation

-0.69

aging

-0.68

POSITIVE LOGITS

arthed

1.17

cker

0.75

quist

0.72

 Sparkle

0.68

cean

0.67

berry

0.65

 Marble

0.64

 buggy

0.64

anu

0.63

Mik

0.61

Activations Density 0.031%

words related to months

the repeated use of the word "une" in various contexts

No Comments

No Known Activations