INDEX

Explanations

verbs related to discovery

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "discover" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oided

-0.77

erate

-0.72

cussion

-0.70

ptic

-0.68

umbn

-0.68

wr

-0.68

 paced

-0.67

ortunately

-0.67

usal

-0.67

req

-0.66

POSITIVE LOGITS

 flaws

0.82

 anew

0.81

æĥ

0.77

Ô

0.72

 Lauder

0.72

ibility

0.71

 unsus

0.70

gdala

0.70

 Scythe

0.70

Discover

0.69

Activations Density 0.052%

verbs related to discovery

occurrences of the word "discover" and its variations

No Comments

No Known Activations