INDEX

Explanations

words related to a specific place or name, specifically "Lin."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lin" 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

awei

-0.87

kward

-0.81

lance

-0.75

rences

-0.70

population

-0.70

rahim

-0.65

endants

-0.63

rieving

-0.62

akening

-0.62

 Seym

-0.61

POSITIVE LOGITS

fo

1.04

 Rouge

0.95

eman

0.93

strument

0.90

ergic

0.88

osaurs

0.83

burg

0.82

ned

0.81

ews

0.81

phrine

0.81

Activations Density 0.084%

words related to a specific place or name, specifically "Lin."

occurrences of the word "lin" in various contexts

No Comments

No Known Activations