INDEX

Explanations

terms related to complexity or intricacy

oai_token-act-pair · gpt-3.5-turbo

references to complexity 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ablishment

-0.77

OIL

-0.76

HI

-0.71

inators

-0.69

ï¸

-0.69

IGH

-0.68

§

-0.67

ĵ

-0.65

Ń·

-0.65

UMP

-0.64

POSITIVE LOGITS

ioned

1.14

ively

0.81

 configurations

0.81

 layered

0.77

ions

0.77

 complexity

0.76

 enough

0.76

 structured

0.74

enegger

0.73

 facets

0.73

Activations Density 0.033%

terms related to complexity or intricacy

references to complexity in various contexts

No Comments

No Known Activations