INDEX

Explanations

words related to a specific name or term (Ter____)

oai_token-act-pair · gpt-3.5-turbo

the presence of the name "Ter" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģ®éŃĶ

-0.84

ħĭ

-0.81

atform

-0.80

issance

-0.77

ãģį

-0.73

uncture

-0.66

ãģ¦

-0.65

unct

-0.63

 business

-0.62

à¥

-0.62

POSITIVE LOGITS

rible

1.41

race

1.20

ribly

1.17

rance

1.16

rence

1.15

restrial

1.09

mine

1.07

rors

1.05

rell

1.05

rier

1.04

Activations Density 0.009%

words related to a specific name or term (Ter____)

the presence of the name "Ter" in various contexts

No Comments

No Known Activations