INDEX

Explanations

occurrences of actions or verbs related to receiving, going, and interacting

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

instances in the text where actions are being described

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WER

-0.63

never

-0.63

 Calculator

-0.62

 Moroc

-0.62

 spared

-0.61

bay

-0.58

ACP

-0.57

;;;;;;;;

-0.57

Neh

-0.56

 Fuller

-0.56

POSITIVE LOGITS

ibrary

0.73

adelphia

0.72

GROUP

0.65

olded

0.65

esta

0.64

irtual

0.61

icles

0.60

lict

0.60

 somebody

0.58

 solo

0.58

Activations Density 0.305%

occurrences of actions or verbs related to receiving, going, and interacting

instances in the text where actions are being described

No Comments

No Known Activations