INDEX

Explanations

actions or attempts

oai_token-act-pair · gpt-3.5-turbo

references to attempts or efforts made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ensable

-0.72

SOURCE

-0.71

involved

-0.65

notice

-0.64

RIP

-0.64

ublic

-0.63

quartered

-0.63

usat

-0.63

vation

-0.63

obal

-0.63

POSITIVE LOGITS

 hypotheses

0.92

 unsuccessfully

0.91

 hypothesis

0.90

 experiment

0.82

 patience

0.82

 prototypes

0.81

 waters

0.80

 unorthodox

0.77

 hardest

0.77

 unconventional

0.76

Activations Density 0.150%

actions or attempts

references to attempts or efforts made by individuals

No Comments

No Known Activations