INDEX

Explanations

phrases related to content sharing restrictions

oai_token-act-pair · gpt-3.5-turbo

terms related to redistribution and distribution policies

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

gone

-0.86

gged

-0.73

tein

-0.70

nea

-0.67

stood

-0.66

 Galile

-0.65

zig

-0.65

footed

-0.64

cius

-0.64

lif

-0.63

POSITIVE LOGITS

 redistributed

0.92

 Vaugh

0.68

 accordingly

0.68

âĢ¦)

0.66

ONSORED

0.66

OUP

0.66

ricting

0.65

imate

0.64

ATED

0.64

daq

0.64

Activations Density 0.014%

phrases related to content sharing restrictions

terms related to redistribution and distribution policies

No Comments

No Known Activations