INDEX

Explanations

words related to a specific entity, specifically "Bor"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Bor" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

encers

-0.83

ITNESS

-0.79

perture

-0.79

 srfAttach

-0.75

ONSORED

-0.74

ULT

-0.73

UAL

-0.72

IDENT

-0.71

 VIDEOS

-0.70

OPE

-0.69

POSITIVE LOGITS

ussia

0.94

chard

0.92

vik

0.87

ham

0.87

bon

0.86

Bor

0.86

wana

0.85

mingham

0.84

rome

0.83

uni

0.82

Activations Density 0.009%

words related to a specific entity, specifically "Bor"

mentions of the name "Bor" across various contexts

No Comments

No Known Activations