INDEX

Explanations

mentions of deputy positions in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to deputy roles 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stakes

-0.92

oven

-0.81

hetti

-0.79

azed

-0.79

ĸļ

-0.78

 Gutenberg

-0.78

oring

-0.76

rust

-0.72

uph

-0.71

yrs

-0.71

POSITIVE LOGITS

uty

1.01

 deputy

0.97

 assistant

0.85

 clerks

0.82

 director

0.79

 sher

0.78

 adjunct

0.77

 chief

0.77

 sheriff

0.76

 Deputy

0.75

Activations Density 0.017%

mentions of deputy positions in various contexts

references to deputy roles in various contexts

No Comments

No Known Activations