INDEX

Explanations

mentions of different states, both physical and logical

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "state" 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

 Flavoring

-0.86

poons

-0.86

 Torn

-0.84

 Carbuncle

-0.78

iffe

-0.74

thora

-0.72

sites

-0.72

odi

-0.72

enic

-0.71

Maw

-0.71

POSITIVE LOGITS

quo

0.96

lessness

0.91

less

0.87

fulness

0.85

ually

0.84

worthiness

0.83

LESS

0.79

liness

0.79

 legislatures

0.77

manship

0.76

Activations Density 0.043%

mentions of different states, both physical and logical

occurrences of the word "state" in various contexts

No Comments

No Known Activations