INDEX

Explanations

terms related to specific attributes or characteristics

oai_token-act-pair · gpt-3.5-turbo

terms related to specificity 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 @ 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

rican

-0.76

Bush

-0.74

former

-0.72

=-=-=-=-

-0.72

ruary

-0.70

Jenn

-0.69

kj

-0.68

NER

-0.68

http

-0.68

TPP

-0.68

POSITIVE LOGITS

ities

1.14

ally

1.04

iveness

0.97

izations

0.89

ivity

0.85

ality

0.85

iations

0.84

itarian

0.83

ileged

0.83

ALLY

0.79

Activations Density 0.020%

terms related to specific attributes or characteristics

terms related to specificity in various contexts

No Comments

No Known Activations