INDEX

Explanations

words related to movement or transportation, especially involving return or reversal of direction

oai_token-act-pair · gpt-3.5-turbo

instances of the word "back"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entric

-0.69

inational

-0.66

ities

-0.64

viz

-0.62

 delegation

-0.62

enaries

-0.61

eria

-0.61

izo

-0.61

ision

-0.61

ifix

-0.59

POSITIVE LOGITS

dated

1.20

packs

1.10

fires

1.07

packing

1.04

fired

1.01

haul

1.01

wards

1.00

GROUND

0.99

doors

0.97

rower

0.96

Activations Density 0.054%

words related to movement or transportation, especially involving return or reversal of direction

instances of the word "back"

No Comments

No Known Activations