INDEX

Explanations

references to specific product names

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific brand or entity associated with a context of events or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

amen

-0.83

anu

-0.81

atem

-0.80

doc

-0.77

pat

-0.75

esar

-0.74

iso

-0.74

manuel

-0.73

hare

-0.73

uador

-0.73

POSITIVE LOGITS

 Storm

1.79

Ops

1.66

Storm

1.65

 Higgins

1.60

 Tornado

1.55

 Spark

1.54

 Vortex

1.53

 Flood

1.46

 Roof

1.44

Fog

1.42

Activations Density 0.051%

references to specific product names

mentions of a specific brand or entity associated with a context of events or individuals

No Comments

No Known Activations