INDEX

Explanations

names of various camps

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific location or establishment, particularly "Camp."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lihood

-0.90

 regress

-0.68

liness

-0.64

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.61

SHIP

-0.61

 accelerator

-0.61

 headlights

-0.59

 traff

-0.58

 superf

-0.58

 republic

-0.58

POSITIVE LOGITS

agna

1.21

aign

1.09

bell

1.09

agne

1.07

ground

0.97

sites

0.97

fires

0.92

ing

0.91

agn

0.89

iday

0.89

Activations Density 0.025%

names of various camps

mentions of a specific location or establishment, particularly "Camp."

No Comments

No Known Activations