INDEX

Explanations

words related to neurology

oai_token-act-pair · gpt-3.5-turbo

terms related to neuroscience

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

UAL

-0.84

 Rack

-0.74

 Goose

-0.73

 Revel

-0.72

 Lynch

-0.72

-0.69

 Abel

-0.69

 Franks

-0.68

INGS

-0.67

ICAN

-0.66

POSITIVE LOGITS

genic

1.18

sci

1.14

scient

1.13

pathic

1.05

phys

1.04

psych

1.04

biology

1.03

chem

1.02

scientific

1.01

 neur

1.00

Activations Density 0.011%

words related to neurology

terms related to neuroscience

No Comments

No Known Activations