INDEX

Explanations

statements indicating proof or verification of a claim

oai_token-act-pair · gpt-3.5-turbo

the phrase "that" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

gur

-0.66

Guard

-0.59

erves

-0.58

 Topics

-0.58

isers

-0.56

Wide

-0.56

MH

-0.55

è»

-0.55

erve

-0.54

estones

-0.54

POSITIVE LOGITS

 contradicts

0.77

 they

0.75

cher

0.73

 fateful

0.65

 pesky

0.64

soever

0.64

we

0.64

 somebody

0.64

 someone

0.63

 proves

0.63

Activations Density 0.286%

statements indicating proof or verification of a claim

the phrase "that" in various contexts

No Comments

No Known Activations