INDEX

Explanations

references to the word "Broad"

oai_token-act-pair · gpt-3.5-turbo

references to "Broad" or "broad" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Downloadha

-0.87

Oro

-0.80

 Tillerson

-0.77

 Frankenstein

-0.77

 Canaver

-0.76

 Mehran

-0.71

 Uriel

-0.69

 Guerrero

-0.66

 Ventura

-0.65

 Hugo

-0.65

POSITIVE LOGITS

bent

1.14

casters

1.12

casting

1.01

band

1.00

stairs

0.99

sheet

0.96

casts

0.96

sheets

0.96

caster

0.92

sword

0.90

Activations Density 0.009%

references to the word "Broad"

references to "Broad" or "broad" in various contexts

No Comments

No Known Activations