INDEX

Explanations

references to microtubules

oai_token-act-pair · gpt-3.5-turbo

mentions of the author Jules Verne

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

hearted

-0.66

 plank

-0.64

 affordability

-0.63

 perception

-0.63

imm

-0.61

Eva

-0.60

 impression

-0.60

ger

-0.59

apt

-0.59

 keeper

-0.58

POSITIVE LOGITS

ules

1.13

utics

0.94

CRIP

0.89

utic

0.87

utical

0.87

uling

0.86

veyard

0.84

ugal

0.82

anwhile

0.82

hner

0.81

Activations Density 0.020%

references to microtubules

mentions of the author Jules Verne

No Comments

No Known Activations