INDEX

Explanations

hyphenated phrases where the second word is a verb

oai_token-act-pair · gpt-3.5-turbo

various forms of the phrase "cut" in negative 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Burr

-0.69

 Chambers

-0.69

 Confederation

-0.68

 Imran

-0.66

Moj

-0.66

KN

-0.64

 throats

-0.64

Lod

-0.61

 revised

-0.61

 hemisphere

-0.61

POSITIVE LOGITS

based

1.26

through

1.09

your

1.08

rate

1.08

level

1.05

to

1.05

type

1.05

luster

1.05

disk

1.04

duty

1.02

Activations Density 0.139%

hyphenated phrases where the second word is a verb

various forms of the phrase "cut" in negative contexts

No Comments

No Known Activations