INDEX

Explanations

phrases related to reasons or causes

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate conditional or causal relationships in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocation

-0.62

warm

-0.60

 uptake

-0.60

farm

-0.59

 lick

-0.59

rises

-0.58

 mailing

-0.58

 nexus

-0.56

wn

-0.56

cano

-0.55

POSITIVE LOGITS

Spoiler

0.76

RANT

0.65

Ã»

0.65

 Bour

0.62

udeb

0.61

haps

0.58

 guessed

0.57

IPS

0.57

 Jong

0.56

ovi

0.56

Activations Density 0.161%

phrases related to reasons or causes

phrases that indicate conditional or causal relationships in the text

No Comments

No Known Activations