INDEX

Explanations

instances where the text mentions specific counties

oai_token-act-pair · gpt-3.5-turbo

references to various counties

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

acles

-0.93

otten

-0.87

furt

-0.85

acity

-0.82

borgh

-0.81

igmatic

-0.80

ugu

-0.78

uous

-0.78

eared

-0.75

ipedia

-0.74

POSITIVE LOGITS

 sheriff

1.11

wide

1.08

 coroner

0.95

 commissioners

0.94

 Sheriff

0.94

 clerk

0.92

 courthouse

0.90

 jails

0.90

 jail

0.85

 parks

0.84

Activations Density 0.024%

instances where the text mentions specific counties

references to various counties

No Comments

No Known Activations