INDEX

Explanations

phrases related to news articles or headlines

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 consensual

-0.77

 stating

-0.60

ometry

-0.59

onse

-0.59

 stated

-0.58

 Representative

-0.58

ire

-0.57

 adamant

-0.57

 joke

-0.57

 congress

-0.56

POSITIVE LOGITS

 Subscribe

1.11

Subscribe

1.02

 subscribe

1.00

NECT

0.82

Visit

0.81

Topics

0.81

 Explore

0.80

 subscribing

0.79

Follow

0.79

scribe

0.78

Activations Density 0.267%

phrases related to news articles or headlines

references to specific individuals or significant events

No Comments

No Known Activations