INDEX

Explanations

objects within a scene or environment

oai_token-act-pair · gpt-3.5-turbo

references to various types of objects in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rawdownloadcloneembedreportprint

-0.76

ECH

-0.73

atorium

-0.69

Revolution

-0.68

ERAL

-0.68

Attempt

-0.67

stream

-0.67

NING

-0.67

Leader

-0.65

oÄŁ

-0.64

POSITIVE LOGITS

poons

1.30

paces

1.18

hips

1.14

mith

1.12

etter

1.11

omething

1.11

hops

1.10

uggest

1.09

cale

1.09

uits

1.06

Activations Density 0.066%

objects within a scene or environment

references to various types of objects in different contexts

No Comments

No Known Activations