INDEX

Explanations

words related to livestock, specifically cattle and sheep

oai_token-act-pair · gpt-3.5-turbo

references to livestock, particularly cattle and sheep

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

AMI

-0.73

 fortun

-0.72

ioxide

-0.72

 Bucc

-0.71

 Fiction

-0.66

SPONSORED

-0.65

 explan

-0.65

OLOGY

-0.63

UM

-0.62

 disadvant

-0.62

POSITIVE LOGITS

 grazing

1.43

 pasture

1.39

 herd

1.32

 graz

1.24

 herds

1.20

skin

1.15

 ranc

1.15

 cattle

1.13

 ranch

1.12

 calves

1.10

Activations Density 0.065%

words related to livestock, specifically cattle and sheep

references to livestock, particularly cattle and sheep

No Comments

No Known Activations