INDEX

Explanations

words related to legal or investigative contexts

oai_token-act-pair · gpt-3.5-turbo

phrases or terms that indicate connections or associations between different topics or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ifter

-0.79

IVER

-0.74

ARD

-0.72

 Muller

-0.70

UGE

-0.68

aneers

-0.68

oufl

-0.67

\\\\\\\\\\\\\\\\

-0.67

ardless

-0.66

Bay

-0.66

POSITIVE LOGITS

 thereto

0.92

ness

0.83

 reconc

0.83

 ancest

0.82

worldly

0.82

 newsp

0.82

 relate

0.80

 unrelated

0.76

 related

0.76

 negatively

0.75

Activations Density 0.020%

words related to legal or investigative contexts

phrases or terms that indicate connections or associations between different topics or concepts

No Comments

No Known Activations