INDEX

Explanations

words related to distraction or shifts in focus

oai_token-act-pair · gpt-3.5-turbo

specific adjectives and descriptors related to color and intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.77

 Akin

-0.77

 commemorate

-0.65

rium

-0.64

 Gandhi

-0.64

 Grassley

-0.63

Fav

-0.63

 whoever

-0.62

advertisement

-0.61

POSITIVE LOGITS

ness

0.98

haired

0.93

hearted

0.92

coat

0.91

lining

0.88

colour

0.86

skinned

0.85

NESS

0.82

headed

0.81

packed

0.80

Activations Density 0.160%

words related to distraction or shifts in focus

specific adjectives and descriptors related to color and intensity

No Comments

No Known Activations