INDEX

Explanations

references to cabins

oai_token-act-pair · gpt-3.5-turbo

references to cabins and related terms

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

ku

-0.71

lda

-0.69

avez

-0.67

thodox

-0.65

FW

-0.65

oppable

-0.64

ammad

-0.63

Uz

-0.63

 GOODMAN

-0.63

henko

-0.63

POSITIVE LOGITS

 cabin

1.22

etry

0.89

 Seat

0.84

illo

0.84

 Cabin

0.84

door

0.82

artment

0.80

 compartment

0.78

igans

0.74

cab

0.72

Activations Density 0.012%

references to cabins

references to cabins and related terms

No Comments

No Known Activations