INDEX

Explanations

sentences

oai_token-act-pair · gpt-3.5-turbo

references to sentences and their structure

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

sie

-0.96

BLIC

-0.92

rous

-0.85

aucus

-0.80

ikarp

-0.78

aucuses

-0.77

rists

-0.77

RIS

-0.75

rament

-0.72

atform

-0.71

POSITIVE LOGITS

 sentences

1.10

 sentence

1.07

 uttered

1.04

 summ

0.84

 phrases

0.75

 paragraphs

0.75

 quotation

0.74

 grammar

0.71

 paragraph

0.69

forestation

0.66

Activations Density 0.015%

sentences

references to sentences and their structure

No Comments

No Known Activations