INDEX

Explanations

mentions of specific locations, particularly in New York

oai_token-act-pair · gpt-3.5-turbo

references to New York locations and entities

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

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

Maker

-0.83

mentioned

-0.67

lvl

-0.65

tumblr

-0.64

height

-0.63

 Horus

-0.62

Appearance

-0.62

struct

-0.61

 Perse

-0.61

ardless

-0.61

POSITIVE LOGITS

.,

0.94

.?

0.83

 Lumpur

0.79

orea

0.74

 ILCS

0.72

.;

0.69

.—

0.69

 ditch

0.68

 Appeals

0.67

 Orchestra

0.66

Activations Density 0.030%

mentions of specific locations, particularly in New York

references to New York locations and entities

No Comments

No Known Activations