INDEX

Explanations

phrases related to neurobiology and medical conditions involving the nervous system

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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

-0.75

REAM

-0.73

 Rack

-0.71

Fif

-0.70

 Revel

-0.70

 Lynch

-0.69

 Tens

-0.68

ablishment

-0.67

 Weaver

-0.66

ICAN

-0.66

POSITIVE LOGITS

sci

1.13

scient

1.12

psych

1.10

genic

1.08

phys

1.06

 neuro

1.04

chem

0.99

typ

0.98

 neur

0.97

pathic

0.97

Activations Density 0.007%

phrases related to neurobiology and medical conditions involving the nervous system

terms related to neuroscience

No Comments

No Known Activations