INDEX

Explanations

words related to connections or restrictions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "bind" and its variations

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

cano

-0.83

asury

-0.76

akura

-0.70

oples

-0.69

ortmund

-0.68

acco

-0.68

 Alto

-0.66

ONSORED

-0.64

issance

-0.64

 Apocalypse

-0.63

POSITIVE LOGITS

sym

1.17

binding

0.98

 bound

0.97

 bind

0.94

ingly

0.91

 binds

0.85

 Binding

0.82

masters

0.81

 binding

0.79

SHIP

0.77

Activations Density 0.018%

words related to connections or restrictions

occurrences of the word "bind" and its variations

No Comments

No Known Activations