INDEX

Explanations

terms related to fragmentation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "fragment" and its derivatives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reon

-0.84

know

-0.74

hiro

-0.73

kins

-0.72

tower

-0.68

rol

-0.67

gio

-0.67

enta

-0.65

ena

-0.64

perm

-0.64

POSITIVE LOGITS

 fragments

0.91

 fracturing

0.88

mentation

0.85

 fractures

0.81

 ILCS

0.77

 fractured

0.76

 Frag

0.75

 fracture

0.75

bite

0.75

 shards

0.73

Activations Density 0.040%

terms related to fragmentation

occurrences of the word "fragment" and its derivatives

No Comments

No Known Activations