INDEX

Explanations

names or abbreviations related to a specific entity, potentially an organization or person, indicated by phrases like "MR," "FF," "PL," and "As"

oai_token-act-pair · gpt-3.5-turbo

mentions of the abbreviation "MR" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

erella

-0.72

 liner

-0.69

stall

-0.69

 Hots

-0.66

 Strait

-0.65

tics

-0.65

ovy

-0.64

vor

-0.64

front

-0.61

aries

-0.61

POSITIVE LOGITS

CTV

0.87

udge

0.82

andom

0.79

senal

0.75

adish

0.70

igue

0.70

aund

0.70

ENA

0.69

agnar

0.68

VP

0.68

Activations Density 0.028%

names or abbreviations related to a specific entity, potentially an organization or person, indicated by phrases like "MR," "FF," "PL," and "As"

mentions of the abbreviation "MR" in various contexts

No Comments

No Known Activations