INDEX

Explanations

words related to physical barriers or obstacles

oai_token-act-pair · gpt-3.5-turbo

terms related to barriers or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

croft

-0.78

-0.72

Accessory

-0.72

 Raise

-0.70

 Hastings

-0.69

 Coffee

-0.66

conn

-0.64

lyss

-0.62

 sched

-0.62

hold

-0.61

POSITIVE LOGITS

etr

1.65

agnetic

1.15

agog

1.04

agonal

1.01

ading

0.99

etrical

0.99

ansky

0.99

kefeller

0.94

obiles

0.93

acers

0.92

Activations Density 0.008%

words related to physical barriers or obstacles

terms related to barriers or constraints

No Comments

No Known Activations