INDEX

Explanations

words related to 'Department' or 'Deputy'

oai_token-act-pair · gpt-3.5-turbo

references to the word "Dep" or its variations, likely indicating a focus on laws, policies, or organizational references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Pose

-0.97

 Hole

-0.86

enegger

-0.82

FORE

-0.78

nings

-0.78

çĦ

-0.77

MER

-0.75

 Dragonbound

-0.72

swick

-0.71

 deaf

-0.71

POSITIVE LOGITS

recated

1.21

artments

1.16

utation

1.15

ository

1.11

uty

1.08

orters

1.07

uties

1.06

osit

1.05

ict

1.05

raved

1.03

Activations Density 0.016%

words related to 'Department' or 'Deputy'

references to the word "Dep" or its variations, likely indicating a focus on laws, policies, or organizational references

No Comments

No Known Activations