INDEX

Explanations

sentences where someone is expressing personal thoughts or actions

oai_token-act-pair · gpt-3.5-turbo

actions related to communication and interaction

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

ratulations

-0.77

 unlaw

-0.71

locks

-0.71

Dot

-0.65

lock

-0.64

gress

-0.64

grave

-0.59

Sov

-0.59

JUST

-0.59

lyak

-0.57

POSITIVE LOGITS

adelphia

0.83

ometimes

0.81

ginx

0.77

advertisement

0.75

 yearly

0.73

pmwiki

0.69

ided

0.69

veland

0.69

 Gleaming

0.66

 weekly

0.65

Activations Density 0.912%

sentences where someone is expressing personal thoughts or actions

actions related to communication and interaction

No Comments

No Known Activations