INDEX

Explanations

phrases related to writing or drawing lines

oai_token-act-pair · gpt-3.5-turbo

repeated references to "line" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CVE

-0.85

sburg

-0.75

sylvania

-0.74

soever

-0.71

ndum

-0.70

ILY

-0.69

CLASSIFIED

-0.69

 unden

-0.68

ILD

-0.68

ntil

-0.67

POSITIVE LOGITS

backer

1.18

aments

1.13

ages

1.10

ups

1.09

breaks

0.85

up

0.83

breakers

0.78

breaking

0.78

points

0.77

lines

0.76

Activations Density 0.052%

phrases related to writing or drawing lines

repeated references to "line" in various contexts

No Comments

No Known Activations